skills/confess/SKILL.md
Invoke this skill BEFORE ending any session, marking a task done, or saying 'complete'. Also invoke when the user says 'are you sure?', 'did you miss anything?', 'anything else?', 'what did I miss?', 'confess', or 'audit your work'. This is a proactive self-audit — do not wait to be asked. Skipping this means shipping incomplete work, broken references, untested paths, or unmentioned concerns the agent noticed but buried. Covers: incomplete changes, untested assumptions, pattern violations, hidden concerns, and cleanup debt.
npx skillsauth add b-open-io/prompts confessInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
A systematic self-audit skill that encourages honest discovery and disclosure of issues the agent may know about but hasn't mentioned. Especially good for admitting to reward hacking and coming clean.
Search for related files that may also need changes:
grep to find references to modified codeBe honest about what was actually verified:
Compare against existing codebase:
globReveal things noticed but not mentioned:
Check for orphaned code:
Do not ask "what did I miss?" — that question invites rationalization.
Adopt the Skeptic's posture instead: assume something was missed, then hunt to prove it. Your job is to disprove your own "done" claim. A Skeptic is penalized for false dismissals, not for being thorough.
Run through this checklist before closing:
Gather Context
# What files were recently modified?
git diff --name-only HEAD~1
# What functions/exports changed?
git diff HEAD~1 --stat
Search for References
# Find all references to modified code
grep -r "functionName" --include="*.ts" --include="*.tsx"
Compare Patterns
Verification Check
Disclose Everything Format confessions as:
## My Confessions
### Incomplete Work
- [specific issue]
### Untested
- [what wasn't verified]
### Pattern Issues
- [inconsistencies found]
### Hidden Concerns
- [things I noticed but didn't mention]
### Cleanup Needed
- [dead code, orphaned files]
After implementing OAuth error handling:
My Confessions
Incomplete Work
- Modified
auth-config.tsbutoauth2/authorize/page.tsx:173still redirects to/error/oauthproxy.ts:67also references the old error routelib/oauth-errors.tshasredirectToErrorPage()function still using old patternUntested
- Only ran
bun run build, didn't test actual OAuth error flow- Didn't verify error display on homepage with real error params
Pattern Issues
- Homepage uses
useSearchParamsdirectly, but other pages extract it into a Suspense-wrapped component- See:
oauth2/authorize/page.tsx,device/page.tsxfor correct patternHidden Concerns
- The error page at
/error/[type]is well-designed and actively used- Removing
onAPIErrormay have been the wrong approachCleanup Needed
- Decision needed: fully migrate to homepage errors OR keep
/error/oauthroute
tools
This skill should be used when a Claude Code session needs to keep working after Anthropic usage runs out, or when the user asks to run the Claude Code harness on GPT-5.6 Sol. Trigger phrases include "my Anthropic usage ran out", "I'm out of Claude usage", "usage limit reached, what now", "keep working on another model", "run Claude Code on GPT-5.6 Sol", "use GPT-5.6 Sol as the model", "set up claudex", "claudex isn't working", "route the harness through CLIProxyAPI", or "bill against my ChatGPT/Codex subscription". It stands up a local proxy so the Claude Code CLI runs on OpenAI's Codex backend as an escape hatch, and diagnoses that setup when it drifts. macOS + Homebrew.
testing
This skill should be used when the user asks to "open Visual Wayfinder", "answer a Wayfinder ticket visually", "turn this decision into a configurator", "show Wayfinder choices as a dashboard", "prototype the Wayfinder questionnaire", or wants interactive choice cards, tradeoff controls, rankings, ranges, toggles, and consequence previews for one active Wayfinder decision. It wraps the Wayfinder skill and JSON Render; it never replaces the tracker or resolves more than the active decision.
development
This skill should be used when the user asks to "make a visual proposal", "write this up so I can share it", "present these options visually", "diagram the trade-offs", "turn this plan into something reviewable", or requests a shareable design pitch, architecture proposal, RFC, options comparison, or visual roadmap for work that has not been built. It produces one self-contained, theme-aware HTML page led by grounded diagrams. Use visual-review instead for completed code changes; do not use this skill for internal task tracking.
tools
This skill should be used when the user asks to "add plugin settings", "make a plugin configurable", "store per-project plugin configuration", "use settings.local.json", "create a plugin state file", "expose skill settings in Agent Master", or "add a skill interface". Distinguishes official Claude Code settings from project-owned configuration and documents bOpen Agent Master skill interface discovery.