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/a8cteam51/claude-code-plugins/pr-addr-feedbackgit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWhat 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 | $0.00047 | $0.00927 |
| Opus 5 | $0.00023 | $0.00464 |
| Sonnet 5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
pr-addr-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 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping the user address unresolved review comments on a GitHub pull request. The PR URL is: $ARGUMENTS
Step 1: Parse the PR URL
Extract owner, repo, and pull_number from the URL. The URL format is:
https://github.com/{owner}/{repo}/pull/{pull_number}
Step 2: Fetch unresolved review threads
Use the GitHub GraphQL API via gh api graphql to fetch all unresolved threads and their comments:
gh api graphql -f query='
{
repository(owner: "OWNER", name: "REPO") {
pullRequest(number: PULL_NUMBER) {
title
headRefName
reviewThreads(first: 100) {
nodes {
id
isResolved
isOutdated
comments(first: 10) {
nodes {
body
path
line
originalLine
diffHunk
author { login }
url
createdAt
}
}
}
}
}
}
}'
Filter to threads where isResolved is false and isOutdated is false. If there are no unresolved threads, tell the user and stop.
Step 3: Show a summary
Before doing anything, print a brief summary:
- PR title and branch
- Number of unresolved threads found
- List of files touched by comments
Then proceed without asking for confirmation.
Step 4: Process each thread
For each unresolved thread, work through the following logic. Process them one at a time, in order.
4a: Read context
Use the Read tool to open the file at path. Focus on the lines referenced in line or originalLine, plus ~15 lines of surrounding context.
Also look at diffHunk from the comment — it shows the exact diff context the reviewer saw.
4b: Evaluate validity
Assess whether the feedback is valid. Consider:
- Is the suggested change technically correct?
- Does it improve clarity, correctness, performance, or security?
- Is it a matter of style/preference with no clear right answer?
- Does the comment contradict the existing codebase patterns?
- Is the comment outdated (e.g., refers to code that no longer exists)?
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 · 111 lines · 47 tokens per session scan A f3e1d7c70cd6
pr-addr-feedback is a command published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 927 once invoked, about $0.0002 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 2026-08-31.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.