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.
npx agentmods add commands/bjcoombs/ai-native-toolkit/fix-prgit clone --depth 1 https://github.com/bjcoombs/ai-native-toolkitWhat 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 | $0.00019 | $0.00790 |
| Opus 5 | $0.00010 | $0.00395 |
| Sonnet 5 | $0.00004 | $0.00158 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
fix-pr 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 2d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix PR Autonomously
Enter autonomous PR review loop for the current branch's PR. Loops until the PR is merge-ready across ALL criteria, not just CI.
What this does
Drive the current branch's PR to merge-ready across all five criteria, then stop for human review (this command does not auto-merge).
Use the pr-review-merge skill: it owns the 5 ready criteria, thread-resolution rules, shell
pitfalls, base-sync-first, and the background CI watcher. Pass the current PR number
(gh pr view --json number --jq '.number') and the base branch
(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'), plus any bot rules
from the project's Marathon Configuration.
Protocol
-
Autonomous Loop (DO NOT ask for permission between iterations):
- Sync base branch, check all 5 criteria, fix issues, push
- Report: "Iteration N: Fixed X issues" or "Iteration N: Waiting for CI"
- Loop until all green
-
Stop when ALL 5 criteria met:
- Report: "PR #X: All criteria met, ready for human review"
- Include status footer
- STOP
-
Only ask for help if:
- Genuinely blocked (ambiguous merge conflict, unclear review feedback)
- After 5+ iterations with no progress
- Need design decision from user
Example Output
🔄 Iteration 1: Checking PR #123...
⚠️ Merge conflict with base branch in App.tsx — resolving (accept both sides)
❌ CI: TypeScript errors in user.service.ts
❌ CodeRabbit: 2 unresolved threads (missing error handling)
Fixing...
🔄 Iteration 2: Checking PR #123...
✅ In sync with base branch
✅ CI passing
❌ CodeRabbit: 1 remaining thread (async pattern)
Fixing...
🔄 Iteration 3: Checking PR #123...
✅ In sync with base branch
✅ CI passing
✅ All threads resolved
✅ No unaddressed comments
✅ PR #123: All 5 criteria met, ready for your review!
---
## 📍 Current Work
🔗 **PR**: #123 - Add payment processing
https://github.com/org/repo/pull/123
📊 **Latest**: All criteria met after 3 iterations
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.
- 2d ago First seen · 104 lines · 19 tokens per session scan A c095cccd9e27
fix-pr is a command published in the GitHub repository bjcoombs/ai-native-toolkit (30 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 790 once invoked, about $0.0001 per session on Opus 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
README
Git workflow and quality assurance commands for the claude-skills repository.
loop
Iteratively fix issues until all resolved or max iterations reached.
OpenSpec: Apply
Implement an approved OpenSpec change and keep tasks in sync.
auto-goal
goal 래퍼 — /goal 생성, 상태 확인, 완료/blocked handoff를 goal tool 또는 slash command로 연결합니다.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
implement-task
根据技术方案实施任务并输出实现报告.