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/jnarowski/agentcmd/implement-pr-feedbackgit clone --depth 1 https://github.com/jnarowski/agentcmdWhat 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 | $0.00013 | $0.01535 |
| Opus 5 | $0.00006 | $0.00767 |
| Sonnet 5 | $0.00003 | $0.00307 |
| Haiku 4.5 | $0.00001 | $0.00153 |
Grade A, and why
implement-pr-feedback 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 today.
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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement PR Feedback
Atomic operation: fetch PR comments → analyze → implement → commit → reply to each thread → auto-resolve.
Variables
- $pr-number: $1 (optional) - PR number (defaults to current branch PR)
Instructions
CRITICAL:
- NEVER skip git hooks (no --no-verify)
- Use HEREDOC for commit message with Claude footer
- Check if changes exist before committing
- Reply to EACH comment thread individually BEFORE resolving
- Skip resolve gracefully if permission denied
- Don't implement outdated comments without user confirmation
- NEVER run additional commands beyond git/gh operations
- NEVER use TodoWrite or Task tools
Workflow
1. Detect PR Number and Repo Info
Run these commands in parallel:
# Get PR number if not provided
gh pr view --json number -q .number
# Get repo owner and name for GraphQL API
gh repo view --json owner,name -q '"\(.owner.login)/\(.name)"'
If no PR found and $pr-number not provided, stop with error: "No PR found for current branch. Please provide PR number."
2. Fetch PR Comments and Reviews
gh pr view $PR_NUMBER --json reviews,reviewThreads
This returns JSON with:
reviews: Array of review objects withstate(APPROVED, CHANGES_REQUESTED, COMMENTED),body,authorreviewThreads: Array of thread objects withisResolved,isOutdated,comments(array withbody,path,line,id,author)
3. Parse and Display Structured Analysis
Parse the JSON to extract actionable comments. Filter and classify:
Filter criteria (actionable comments):
isResolved === falseisOutdated === false- NOT just approval/LGTM comments
Priority classification (based on keywords in comment body):
- High: Review state is
CHANGES_REQUESTED, or body contains "must", "required", "blocking", "needs", "have to" - Medium: Body contains "should", "consider", "suggest", "recommend", "could you", "please"
- Low: Body contains "?", "why", "how come", "curious"
Display structured analysis like this:
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.
- today First seen · 223 lines · 13 tokens per session scan A 20d57fdce0aa
implement-pr-feedback is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 1,535 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 2026-09-01.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.