Trevin Chow a77fd8c29b fix(ce-plan): size plans from usage and stop trimming requested scope ...

Plans committed guards, retries, modes, and runbooks nobody asked for,
and on ambitious requests narrowed features the user explicitly asked
for. Remove the instructions that asked for more, add a usage-first
sizing test that never trims requested scope, route deepening,
research, and review findings through it, and run ce-doc-review's
scope-guardian on every plan in both directions.

The eval harness gains --with-skill companions and --reasoning-effort
for Grok, plus a ce-plan sizing pack with blind-graded results.

2026-09-28 21:34:10 -07:00

..

fixtures

fix(ci): make a hung Windows smoke step report itself (#1795)

2026-09-28 08:58:55 -07:00

helpers

fix(test): fail CI test stalls fast and stop orphans holding test output (#1787)

2026-09-28 01:40:47 -07:00

skill-eval-cell

fix(ce-plan): size plans from usage and stop trimming requested scope

2026-09-28 21:34:10 -07:00

skills

fix(test): read jobId from overrides in the ce-work harness (#1790)

2026-09-28 02:15:10 -07:00

antigravity-converter.test.ts

feat(antigravity): replace retired Gemini CLI target with Antigravity (agy) (#978)

2026-06-23 00:40:53 -07:00

antigravity-writer.test.ts

feat(antigravity): replace retired Gemini CLI target with Antigravity (agy) (#978)

2026-06-23 00:40:53 -07:00

bundled-script-line-endings.test.ts

fix(skills): force LF line endings on bundled shell and python scripts (#1263)

2026-07-28 12:31:42 -07:00

ce-babysit-pr-contract.test.ts

fix(resolve-pr-feedback): adjudicate judgment calls before escalating (#1765)

2026-09-22 14:38:58 -07:00

ce-babysit-pr-snapshot.test.ts

fix(ce-babysit-pr): corroborate terminal check runs (#1754)

2026-09-21 15:35:59 -07:00

ce-babysit-pr-watch-bootstrap.test.ts

fix(babysit): harden the post-PR handoff, ready reporting, and drafts (#1293)

2026-07-31 11:41:00 -07:00

ce-code-review-mechanics.test.ts

fix(ce-code-review): cut spine cost, log stage cost, focus CI changes (#1723)

2026-09-15 16:49:37 -07:00

ce-code-review-run-log.test.ts

fix(ce-code-review): cut spine cost, log stage cost, focus CI changes (#1723)

2026-09-15 16:49:37 -07:00

ce-commit-contract.test.ts

fix(ce-commit): make the stage-and-commit example PowerShell-safe (#1587)

2026-08-31 10:56:27 -07:00

ce-setup-instruction-file-offers.test.ts

feat(ce-noslop): add the plain-prose skill and route sibling prose through it (#1653)

2026-09-08 14:56:52 -07:00

ce-sweep-analyzer-parity.test.ts

fix(skills): complete below-cap refactor sweep (#1490)

2026-08-19 19:34:17 -07:00

ce-test-browser-driver-policy.test.ts

fix(guides): keep catalog out of the plugin skills tree (#1571)

2026-08-28 16:15:16 -05:00

claude-parser.test.ts

fix(marketplace): unblock Claude Desktop installation (#1163)

2026-07-16 17:33:20 -07:00

cli.test.ts

perf(tests): reuse seed git fixtures to cut suite wall time (#1548)

2026-08-26 22:14:16 -07:00

cline-install-skills.test.ts

fix(lfg): allow agent invocation for the autonomous brainstorm handoff (#1116)

2026-07-12 22:46:07 -07:00

codex-agents.test.ts

fix(cli): strip legacy Codex tool map instead of upserting it (#1118)

2026-07-13 00:28:28 -07:00

codex-content.test.ts

fix(codex-content): preserve URLs and mention-like text (#1254)

2026-07-29 15:04:38 -07:00

codex-converter.test.ts

refactor(agents): flatten agents directory (#621)

2026-04-21 02:35:21 -07:00

codex-dev.test.ts

fix(codex): reconcile config-only plugin installs (#1599)

2026-08-31 00:38:32 -07:00

codex-skill-prompt-budget.test.ts

docs(agent-plugins): attribute the 8000-byte skill cap to its real owner (#1511)

2026-08-22 00:32:13 -07:00

codex-writer.test.ts

fix(targets): guard writers against ancestor-symlink traversal on install (#1100)

2026-07-12 00:27:19 -07:00

commit-push-pr-contract.test.ts

test(ce-commit-push-pr): allow harmless preservation labels (#1675)

2026-09-11 23:57:58 -07:00

commit-push-pr-worktree-safety.test.ts

test(ce-commit-push-pr): allow harmless preservation labels (#1675)

2026-09-11 23:57:58 -07:00

compound-support-files.test.ts

feat(ce-compound): learnings name their retirement condition (#1772)

2026-09-24 11:56:10 -05:00

config-layers-rule-parity.test.ts

fix(skills): honor the standing babysit opt-out and cut the watch's cost (#1609)

2026-09-01 08:59:33 -07:00

converter.test.ts

fix(cli): map sonnet alias to Claude Sonnet 5.5 (#1796)

2026-09-28 12:08:54 -07:00

copilot-converter.test.ts

chore(ce-work-beta): remove beta Codex-delegation skill (#1013)

2026-06-26 14:21:09 -07:00

cross-model-receipt-parity.test.ts

feat(ce-pov): add repository-grounded model panels (#1145)

2026-07-15 17:29:49 -07:00

cross-model-recover-findings-parity.test.ts

fix(ce-code-review): make codex stdout-recovery JSON extractor string-aware (#1207)

2026-07-20 22:17:25 -07:00

detect-tools.test.ts

feat(omp): add native marketplace and skill support (#1358)

2026-08-12 11:30:04 -07:00

doc-claims-validator.test.ts

fix(validate-doc-claims): stop reporting session ids as fabricated SHAs (#1608)

2026-09-01 09:01:33 -07:00

docs-root-literals.test.ts

fix(guides): keep catalog out of the plugin skills tree (#1571)

2026-08-28 16:15:16 -05:00

docs-root-rule-parity.test.ts

feat: add experimental Bake-off approach comparison (#1652)

2026-09-08 09:49:12 -07:00

droid-converter.test.ts

fix(droid): match tool names on word boundaries when inferring agent tools (#1176)

2026-07-19 13:47:12 -07:00

durable-bar-parity.test.ts

docs(solutions): cull learnings that fail the ce-compound bar (#1625)

2026-09-03 12:11:49 -07:00

frontmatter-validator.test.ts

refactor(plugin): make plugin skills-only and root-native (#967)

2026-06-22 00:19:45 -07:00

frontmatter.test.ts

feat(wtf): explain the last message or a supplied source plainly (#1737)

2026-09-18 12:00:46 -07:00

gpt-5-6-skill-migration.test.ts

fix(models): target GPT-6 Sol and Luna for Codex peers and examples (#1762)

2026-09-22 12:08:21 -07:00

kiro-converter.test.ts

fix(kiro): don't rewrite absolute paths as slash command skill refs (#1171)

2026-07-20 23:47:11 -07:00

kiro-writer.test.ts

refactor(plugin): make plugin skills-only and root-native (#967)

2026-06-22 00:19:45 -07:00

legacy-cleanup.test.ts

docs(ce-work): surface return-to-caller mode for outer orchestrators (#1106)

2026-07-13 19:24:30 -07:00

legacy-registry-invariants.test.ts

docs(guides): move skill catalog from docs/skills to skills/guides (#1551)

2026-08-26 19:37:39 -05:00

manifest-path-safety.test.ts

refactor(install): prefer native plugin install across targets (#609)

2026-04-20 18:47:07 -07:00

model-utils.test.ts

fix(cli): map sonnet alias to Claude Sonnet 5.5 (#1796)

2026-09-28 12:08:54 -07:00

omp-native-install.test.ts

docs(guides): move skill catalog from docs/skills to skills/guides (#1551)

2026-08-26 19:37:39 -05:00

opencode-plugin-commands.test.ts

fix(opencode): register skills and commands on OpenCode V2 package installs (#1744)

2026-09-21 13:30:08 -07:00

opencode-plugin.test.ts

fix(opencode): register skills and commands on OpenCode V2 package installs (#1744)

2026-09-21 13:30:08 -07:00

opencode-writer.test.ts

fix(targets): guard writers against ancestor-symlink traversal on install (#1100)

2026-07-12 00:27:19 -07:00

path-sanitization.test.ts

refactor(plugin): make plugin skills-only and root-native (#967)

2026-06-22 00:19:45 -07:00

peer-job-runner-parity.test.ts

fix(cross-model): drop empty Codex usage files and unblock heartbeat teardown (#1533)

2026-08-24 12:37:15 -07:00

peer-job-runner-retry-gate.test.ts

fix(ci): absorb the windows _ctypes flake without hiding real failures (#1605)

2026-08-31 14:26:06 -07:00

pi-converter.test.ts

fix(marketplace): unblock Claude Desktop installation (#1163)

2026-07-16 17:33:20 -07:00

pi-writer.test.ts

fix(targets): guard writers against ancestor-symlink traversal on install (#1100)

2026-07-12 00:27:19 -07:00

pipeline-review-contract.test.ts

fix(models): target GPT-6 Sol and Luna for Codex peers and examples (#1762)

2026-09-22 12:08:21 -07:00

plugin-legacy-artifacts.test.ts

chore(ce-work-beta): remove beta Codex-delegation skill (#1013)

2026-06-26 14:21:09 -07:00

plugin-path.test.ts

perf(tests): reuse seed git fixtures to cut suite wall time (#1548)

2026-08-26 22:14:16 -07:00

pov-skill-contract.test.ts

fix: reduce review noise and clarify agent communication (#1657)

2026-09-09 18:23:59 -07:00

real-plugin-conversion.test.ts

docs(agent-plugins): attribute the 8000-byte skill cap to its real owner (#1511)

2026-08-22 00:32:13 -07:00

reasoning-elevation-parity.test.ts

fix: honor active model-config keys in skill runs (surface + salience) (#1489)

2026-08-20 20:28:11 -07:00

release-components.test.ts

feat: add native Devin CLI plugin support (#1062)

2026-07-09 14:13:52 -07:00

release-config.test.ts

fix(release): include refactors in release notes (#970)

2026-06-22 09:40:07 -07:00

release-metadata.test.ts

feat(wtf): explain the last message or a supplied source plainly (#1737)

2026-09-18 12:00:46 -07:00

release-preview.test.ts

feat: add native Devin CLI plugin support (#1062)

2026-07-09 14:13:52 -07:00

repo-local-ce-skill-work.test.ts

fix(ce-skill-work): require mechanism-led skill descriptions (#1645)

2026-09-07 01:07:09 -07:00

repo-research-analyst-contract.test.ts

fix(ce-plan): 71% smaller SKILL.md, five phase references carry the rest (#1470)

2026-08-18 22:09:30 -07:00

resolve-home.test.ts

fix(cli): expand "~/" home shorthand on Windows (#1055)

2026-07-08 00:26:23 -07:00

resolve-output.test.ts

fix(codex): respect CODEX_HOME for profile installs (#830)

2026-05-14 09:03:45 -07:00

resolve-pr-feedback-pagination.test.ts

fix(ce-resolve-pr-feedback): keep replies out of pending reviews (#1491)

2026-08-20 10:13:57 -07:00

review-skill-contract.test.ts

fix(ce-code-review): flag unrequested behavior rules as advisory (#1771)

2026-09-24 11:57:03 -05:00

run-tests-script.test.ts

fix(test): fail CI test stalls fast and stop orphans holding test output (#1787)

2026-09-28 01:40:47 -07:00

scratch-root-contract.test.ts

fix(guides): keep catalog out of the plugin skills tree (#1571)

2026-08-28 16:15:16 -05:00

scratch-root-preamble-executes.test.ts

feat: add experimental Bake-off approach comparison (#1652)

2026-09-08 09:49:12 -07:00

session-history-scripts.test.ts

fix(ce-compound): read past the resumed-session preamble in extract-metadata (#1736)

2026-09-18 12:22:05 -07:00

settled-decisions-parity.test.ts

feat(pipeline): carry session-settled decisions across the pipeline (#1136)

2026-07-14 14:45:08 -07:00

site-scaffold.test.ts

feat(site): publish the docs site at every.to/compound-engineering (#1664)

2026-09-09 18:38:12 -05:00

skill-agent-ce-prefix.test.ts

feat(wtf): explain the last message or a supplied source plainly (#1737)

2026-09-18 12:00:46 -07:00

skill-conventions.test.ts

fix(ce-code-review): pin in-process fallback coverage wording (#1733)

2026-09-18 15:23:54 -07:00

skill-shell-safety.test.ts

docs(guides): move skill catalog from docs/skills to skills/guides (#1551)

2026-08-26 19:37:39 -05:00

slash-command.test.ts

refactor(cli): converge the slash-command path guard into one helper (#1227)

2026-07-21 22:29:02 -07:00

sweep-state.test.ts

fix(ce-sweep): open state files with explicit UTF-8 encoding (#1321)

2026-08-04 15:13:50 -07:00