<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/skills/test-driven-development, branch claude-code-platform-reference</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>feat(tdd): the project's suite defines green, not just your test file</title>
<updated>2026-08-08T01:44:56+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-08-08T01:44:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=a45ede8ddc0e0545a788868c83814b9d01fbf312'/>
<id>a45ede8ddc0e0545a788868c83814b9d01fbf312</id>
<content type='text'>
At the Verify GREEN moment, redefine "other tests still pass": run the
project's test command even when the task named only one test file — a
scope statement bounds the deliverable, not the verification — and any
failure seen goes in the report by name. In a pre-registered 24-rep
battery on an adjacent-breakage probe, controls ran the wider suite in
1/12 sessions; with this text, 8/12 (sonnet 4/4, kimi 3/4, glm 1/4),
and every session that saw the failure reported it.

Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
At the Verify GREEN moment, redefine "other tests still pass": run the
project's test command even when the task named only one test file — a
scope statement bounds the deliverable, not the verification — and any
failure seen goes in the report by name. In a pre-registered 24-rep
battery on an adjacent-breakage probe, controls ran the wider suite in
1/12 sessions; with this text, 8/12 (sonnet 4/4, kimi 3/4, glm 1/4),
and every session that saw the failure reported it.

Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor(skills): fold TDD Why Order Matters rebuttals into rationalization table</title>
<updated>2026-07-14T22:02:16+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:30:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=4562d18dcfc1ff7c65ec9aae5848539532724a1d'/>
<id>4562d18dcfc1ff7c65ec9aae5848539532724a1d</id>
<content type='text'>
The eval verdict on this cut: deleting Why Order Matters and trusting the
compressed one-line table rows measurably degrades test-first behavior under
the exact pressure the section rebutted ("just write it, tests after") —
control 8/10 → treatment 5/10 at n=10, corroborated on both Claude and Codex.
Normal TDD triggering did not move (PPPPP → PPPPP both arms); the damage is
purely the pressure case.

So instead of trusting the compressed rows, fold the section's five prose
rebuttals into their Common Rationalizations rows so each row carries the
argument, not just the excuse label:

- "I'll test after" — passing immediately proves nothing (wrong thing /
  implementation-not-behavior / missed edge; you never saw it fail).
- "Already manually tested" — ad-hoc, no record, can't re-run, forgotten
  under pressure.
- "Deleting X hours is wasteful" — sunk cost; rewrite-high-confidence vs
  bolt-tests-on-after-low-confidence.
- "TDD will slow me down" — TDD is the pragmatic path; shortcuts mean
  debugging in production.
- "Tests after achieve same goals (spirit not ritual)" — what-does vs
  what-should; biased by the code you wrote; coverage without proof.

Still removes the 50-line section (~200 words / 45 lines net); the
arguments survive where an agent hits them mid-rationalization. Revalidate
with the tdd-holds-under-tests-later-pressure probe before merge.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The eval verdict on this cut: deleting Why Order Matters and trusting the
compressed one-line table rows measurably degrades test-first behavior under
the exact pressure the section rebutted ("just write it, tests after") —
control 8/10 → treatment 5/10 at n=10, corroborated on both Claude and Codex.
Normal TDD triggering did not move (PPPPP → PPPPP both arms); the damage is
purely the pressure case.

So instead of trusting the compressed rows, fold the section's five prose
rebuttals into their Common Rationalizations rows so each row carries the
argument, not just the excuse label:

- "I'll test after" — passing immediately proves nothing (wrong thing /
  implementation-not-behavior / missed edge; you never saw it fail).
- "Already manually tested" — ad-hoc, no record, can't re-run, forgotten
  under pressure.
- "Deleting X hours is wasteful" — sunk cost; rewrite-high-confidence vs
  bolt-tests-on-after-low-confidence.
- "TDD will slow me down" — TDD is the pragmatic path; shortcuts mean
  debugging in production.
- "Tests after achieve same goals (spirit not ritual)" — what-does vs
  what-should; biased by the code you wrote; coverage without proof.

Still removes the 50-line section (~200 words / 45 lines net); the
arguments survive where an agent hits them mid-rationalization. Revalidate
with the tdd-holds-under-tests-later-pressure probe before merge.
</pre>
</div>
</content>
</entry>
<entry>
<title>experiment: ground-up two-principle rewrite of writing-good-tests</title>
<updated>2026-07-13T21:25:55+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T22:47:55+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=92164e2d1a1eb8aa78113202030191e499f0590d'/>
<id>92164e2d1a1eb8aa78113202030191e499f0590d</id>
<content type='text'>
Re-derived from scratch: every rule becomes a corollary of two principles
(every test names the break it catches; every test exercises the real
thing), one consolidated gate per principle, four example pairs kept, the
rest carried by prose. Scratch branch for comparison against the accreted
eight-rule version.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Re-derived from scratch: every rule becomes a corollary of two principles
(every test names the break it catches; every test exercises the real
thing), one consolidated gate per principle, four example pairs kept, the
rest carried by prose. Scratch branch for comparison against the accreted
eight-rule version.
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor(skills): compress writing-good-tests additions; doc changes earn no tests</title>
<updated>2026-07-13T21:25:55+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T21:47:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=5431cf3b1dbba93cce32ea47ea3ff84a87ff885f'/>
<id>5431cf3b1dbba93cce32ea47ea3ff84a87ff885f</id>
<content type='text'>
Prose additions from the last two passes tightened to the terse guard
form: change-detector rule, string-presence trap, and Rule 7's release
valve each drop to a few sentences. Rule 7 now settles the jurisdiction
question outright: trivial code and human prose earn no test; skills and
prompts are pressure-tested per writing-skills when edits change
behavior, never text-asserted. Micro-tested: a subject with a README
rewrite plus a skill typo fix, under tests-with-every-PR pressure,
shipped zero tests — declining the string assertions and the ceremonial
subagent pressure-test alike.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Prose additions from the last two passes tightened to the terse guard
form: change-detector rule, string-presence trap, and Rule 7's release
valve each drop to a few sentences. Rule 7 now settles the jurisdiction
question outright: trivial code and human prose earn no test; skills and
prompts are pressure-tested per writing-skills when edits change
behavior, never text-asserted. Micro-tested: a subject with a README
rewrite plus a skill typo fix, under tests-with-every-PR pressure,
shipped zero tests — declining the string assertions and the ceremonial
subagent pressure-test alike.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(skills): close the change-detector hole in writing-good-tests</title>
<updated>2026-07-13T21:25:55+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T20:03:35+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=cb830c74fb7466951d1593c9a02db9a64a498aa0'/>
<id>cb830c74fb7466951d1593c9a02db9a64a498aa0</id>
<content type='text'>
Fresh-eyes review found falsifiable-but-worthless tests passed every
rule: a constant assertion can fail, uses a literal, mocks nothing — and
protects nothing, firing on intentional decisions while sleeping through
bugs. Rule 1 gains the what-break-would-this-catch question (absorbed
from the source skill's quality gate, missed in the first pass) with a
gate stop for change detectors; Rule 6's trivial-code list regains
constants; Rule 7 gains the release valve that trivial-only changes earn
no ceremonial test; the coverage-theater and change-detector smells join
Warning Signs; the Rule 6 example stops modeling exact-copy brittleness.
Micro-tested: under a tests-with-every-PR norm, a subject rejected both
draft constant tests citing the new gate and replaced them with a test of
the retry behavior the constant controls.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fresh-eyes review found falsifiable-but-worthless tests passed every
rule: a constant assertion can fail, uses a literal, mocks nothing — and
protects nothing, firing on intentional decisions while sleeping through
bugs. Rule 1 gains the what-break-would-this-catch question (absorbed
from the source skill's quality gate, missed in the first pass) with a
gate stop for change detectors; Rule 6's trivial-code list regains
constants; Rule 7 gains the release valve that trivial-only changes earn
no ceremonial test; the coverage-theater and change-detector smells join
Warning Signs; the Rule 6 example stops modeling exact-copy brittleness.
Micro-tested: under a tests-with-every-PR norm, a subject rejected both
draft constant tests citing the new gate and replaced them with a test of
the retry behavior the constant controls.
</pre>
</div>
</content>
</entry>
<entry>
<title>feat(skills): absorb falsifiability discipline into writing-good-tests</title>
<updated>2026-07-13T21:25:55+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:59:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=6a2d0c211f79e64dfcbc83277072e9a0a29db17c'/>
<id>6a2d0c211f79e64dfcbc83277072e9a0a29db17c</id>
<content type='text'>
Generalized from agentsview's testing-without-tautologies skill: a new
Iron Law and lead rule (name the production change that would fail the
test, derive expectations independently of the code under test), a
test-your-code-not-the-framework rule with the characterization-test
exception and the trivial-code guidance, branch-specific doubles folded
into Mock at the Right Level, a closing Mutation Check, and six new
warning-sign smells. Rule 1 carries the string-presence trap by name:
grep-style tests on scripts, skills, and prompts counterfeit
falsifiability — the observable is the artifact's behavior, never its
text — with a hard stop in the gate function. Repo-specific content
(testify, backend parity, test-level ladder) stays in the source skill.
Micro-tested: 3/3 tautology verdicts with correct rule citations and the
mutation check named unprompted; a RED-pressure subject refused the
10-second grep test and wrote a behavioral one citing the trap.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Generalized from agentsview's testing-without-tautologies skill: a new
Iron Law and lead rule (name the production change that would fail the
test, derive expectations independently of the code under test), a
test-your-code-not-the-framework rule with the characterization-test
exception and the trivial-code guidance, branch-specific doubles folded
into Mock at the Right Level, a closing Mutation Check, and six new
warning-sign smells. Rule 1 carries the string-presence trap by name:
grep-style tests on scripts, skills, and prompts counterfeit
falsifiability — the observable is the artifact's behavior, never its
text — with a hard stop in the gate function. Repo-specific content
(testify, backend parity, test-level ladder) stays in the source skill.
Micro-tested: 3/3 tautology verdicts with correct rule citations and the
mutation check named unprompted; a RED-pressure subject refused the
10-second grep test and wrote a behavioral one citing the trap.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(skills): broaden writing-good-tests trigger to any test writing</title>
<updated>2026-07-13T21:25:55+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:51:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=6a8869c7d2f0fead8ceba1a02271b6a5c596cea1'/>
<id>6a8869c7d2f0fead8ceba1a02271b6a5c596cea1</id>
<content type='text'>
The pointer fired only on adding mocks or test utilities; the doc's own
load-when line already says writing or changing tests. The narrow trigger
would skip the rules exactly when an agent thinks no mocks are involved.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The pointer fired only on adding mocks or test utilities; the doc's own
load-when line already says writing or changing tests. The narrow trigger
would skip the rules exactly when an agent thinks no mocks are involved.
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor(skills): reframe testing-anti-patterns as writing-good-tests</title>
<updated>2026-07-13T21:25:55+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:49:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=40b2f3aacaa9ee228cba95146c7c0c14c0e1531d'/>
<id>40b2f3aacaa9ee228cba95146c7c0c14c0e1531d</id>
<content type='text'>
The disclosure doc becomes a catalog of what to do: six positively named
rules (assert on real behavior, cleanup in test utilities, mock at the
right level, mirror real data, tests ship with implementation, prefer
real components), each leading with the GOOD example and keeping the
violation as contrast. Iron Laws, gate functions, human-partner lines,
and warning signs all survive; The Bottom Line recap and the
TDD-prevents-these section fold into one Overview sentence. SKILL.md's
pointer moves into the Good Tests section it belongs with. Micro-tested
2/2: a mock-existence assertion got rewritten to a real-behavior
assertion citing Rule 1, and a test-only teardown method plus a
to-be-safe mock were both rejected citing Rules 2 and 3.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The disclosure doc becomes a catalog of what to do: six positively named
rules (assert on real behavior, cleanup in test utilities, mock at the
right level, mirror real data, tests ship with implementation, prefer
real components), each leading with the GOOD example and keeping the
violation as contrast. Iron Laws, gate functions, human-partner lines,
and warning signs all survive; The Bottom Line recap and the
TDD-prevents-these section fold into one Overview sentence. SKILL.md's
pointer moves into the Good Tests section it belongs with. Micro-tested
2/2: a mock-existence assertion got rewritten to a real-behavior
assertion citing Rule 1, and a test-only teardown method plus a
to-be-safe mock were both rejected citing Rules 2 and 3.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(tdd): link testing anti-patterns reference (#1532)</title>
<updated>2026-06-16T17:09:43+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-05-13T00:22:42+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=9ea7e2b6cb27161545e8d906aebd831d5311f5dd'/>
<id>9ea7e2b6cb27161545e8d906aebd831d5311f5dd</id>
<content type='text'>
Fixes #1529.</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fixes #1529.</pre>
</div>
</content>
</entry>
<entry>
<title>Fix skill descriptions: remove workflow summaries that override flowcharts</title>
<updated>2025-12-18T00:44:52+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-12-12T04:41:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=030a222af19c1f3a93c6eb876a7422d8e4fc0162'/>
<id>030a222af19c1f3a93c6eb876a7422d8e4fc0162</id>
<content type='text'>
Testing revealed that descriptions summarizing workflow cause Claude to
follow the description instead of reading the skill body. Changed all
descriptions to "when to use" triggers only:

- dispatching-parallel-agents: 2+ independent tasks without shared state
- executing-plans: have a written plan to execute with review checkpoints
- requesting-code-review: completing tasks, features, or before merging
- systematic-debugging: encountering bugs before proposing fixes
- test-driven-development: implementing features before writing code
- writing-plans: have spec/requirements for multi-step task before coding
- writing-skills: updated with "description trap" documentation

The description trap: workflow summaries in descriptions create shortcuts
Claude takes, skipping the skill body entirely.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Testing revealed that descriptions summarizing workflow cause Claude to
follow the description instead of reading the skill body. Changed all
descriptions to "when to use" triggers only:

- dispatching-parallel-agents: 2+ independent tasks without shared state
- executing-plans: have a written plan to execute with review checkpoints
- requesting-code-review: completing tasks, features, or before merging
- systematic-debugging: encountering bugs before proposing fixes
- test-driven-development: implementing features before writing code
- writing-plans: have spec/requirements for multi-step task before coding
- writing-skills: updated with "description trap" documentation

The description trap: workflow summaries in descriptions create shortcuts
Claude takes, skipping the skill body entirely.
</pre>
</div>
</content>
</entry>
</feed>
