PAUL is a structured development workflow for Claude Code that organizes AI-assisted work into planning, implementation, and state-reconciliation steps. It is for developers who want acceptance criteria, managed context, and completed plans while building software with Claude Code. Its catalogue entries are commands that implement the workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/ChristopherKahler/paulWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/christopherkahler/paul/plan-fix)<a href="https://agentmods.dev/commands/christopherkahler/paul/plan-fix"><img src="https://agentmods.dev/badge/commands/christopherkahler/paul/plan-fix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/christopherkahler/paul/plan-fix"><img src="https://agentmods.dev/badge/commands/christopherkahler/paul/plan-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.01252 |
| Opus 5.5 | $0.00006 | $0.00501 |
| Sonnet 5.5 | $0.00003 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
paul:plan-fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use: After /paul:verify logs issues to phase-scoped UAT file.
Output: {plan}-FIX.md in the phase directory, ready for execution.
<execution_context>
@/.claude/paul-framework/references/plan-format.md
@/.claude/paul-framework/references/checkpoints.md
</execution_context>
@.paul/STATE.md @.paul/ROADMAP.md
$ARGUMENTS should be a plan number like "04-02" or "10-01". Extract phase number (XX) and plan number (NN).
If no argument provided:
Error: Plan number required.
Usage: /paul:plan-fix 04-02
This creates a fix plan from .paul/phases/XX-name/{plan}-UAT.md
Exit.
Search for matching UAT file:
ls .paul/phases/*/{plan}-UAT.md 2>/dev/null
If not found:
No UAT.md found for plan {plan}.
UAT.md files are created by /paul:verify when testing finds issues.
If no issues were found during testing, no fix plan is needed.
Exit.
Read the UAT.md file. Parse each issue:
- ID (UAT-NNN)
- Title
- Severity (Blocker/Major/Minor/Cosmetic)
- Description/steps to reproduce
- AC reference
Count total issues by severity.
For each issue (or logical group):
- Create one task per issue OR
- Group related minor issues into single task
Task structure:
<task type="auto">
<name>Fix UAT-001: [issue title]</name>
<files>[affected files from issue]</files>
<action>
[What to fix based on issue description]
[Reference original acceptance criteria]
</action>
<verify>[Test that issue is resolved]</verify>
<done>[Issue acceptance criteria met]</done>
</task>
Prioritize: Blocker → Major → Minor → Cosmetic
Create .paul/phases/XX-name/{plan}-FIX.md:
---
phase: XX-name
plan: {plan}-FIX
type: fix
wave: 1
depends_on: []
files_modified: [files from issues]
autonomous: true
---
<objective>
## Goal
Fix {N} UAT issues from plan {plan}.
## Purpose
Address issues discovered during user acceptance testing.
## Output
All issues resolved, ready for re-verification.
Source: {plan}-UAT.md
Priority: {blocker count} blocker, {major count} major, {minor count} minor, {cosmetic count} cosmetic
</objective>
<context>
@.paul/STATE.md
@.paul/ROADMAP.md
**Issues being fixed:**
@.paul/phases/XX-name/{plan}-UAT.md
**Original plan for reference:**
@.paul/phases/XX-name/{plan}-PLAN.md
</context>
<acceptance_criteria>
[Generate AC from issues - each issue becomes an AC]
</acceptance_criteria>
<tasks>
[Generated fix tasks]
</tasks>
<boundaries>
## DO NOT CHANGE
- Files not related to the issues
- Core functionality that passed testing
## SCOPE LIMITS
- Only fix issues from {plan}-UAT.md
- No scope creep or additional improvements
</boundaries>
<verification>
Before declaring plan complete:
- [ ] All blocker issues fixed
- [ ] All major issues fixed
- [ ] Minor/cosmetic issues fixed or documented as deferred
- [ ] Original acceptance criteria from issues met
</verification>
<success_criteria>
- All UAT issues from {plan}-UAT.md addressed
- Ready for re-verification with /paul:verify
</success_criteria>
<output>
After completion, create `.paul/phases/XX-name/{plan}-FIX-SUMMARY.md`
</output>
════════════════════════════════════════
FIX PLAN CREATED
════════════════════════════════════════
{plan}-FIX.md — {N} issues to fix
| Severity | Count |
|----------|-------|
| Blocker | {n} |
| Major | {n} |
| Minor | {n} |
| Cosmetic | {n} |
────────────────────────────────────────
Continue to APPLY?
[1] Approved, run APPLY | [2] Review first | [3] Pause here
────────────────────────────────────────
Use AskUserQuestion to get response.
If approved: /paul:apply .paul/phases/XX-name/{plan}-FIX.md
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 217 lines · 15 tokens per session scan A 7c05d190bf09
paul:plan-fix is a command published in the GitHub repository ChristopherKahler/paul (1,257 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,252 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
f5-gate
Quality gate management with evidence collection.
_test-shared
Shared testing patterns and templates (internal).
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
kill-mutants
Analyze surviving mutants from a mutation testing run and write targeted unit tests to kill them. Re-runs mutations to confirm kills.
generate-widget
Génération Widget Flutter avec Tests.
test-suite
Run comprehensive test suite with coverage analysis.