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 skills add octopusreview/octopus-plugin --skill autofixgit clone --depth 1 https://github.com/octopusreview/octopus-pluginWrote 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/skills/octopusreview/octopus-plugin/autofix)<a href="https://agentmods.dev/skills/octopusreview/octopus-plugin/autofix"><img src="https://agentmods.dev/badge/skills/octopusreview/octopus-plugin/autofix/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/skills/octopusreview/octopus-plugin/autofix"><img src="https://agentmods.dev/badge/skills/octopusreview/octopus-plugin/autofix.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 | $0.00063 | $0.01452 |
| Opus 5 | $0.00032 | $0.00726 |
| Sonnet 5 | $0.00013 | $0.00290 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
autofix 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 11d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octopus Autofix
Review all open PRs for pending reviews and requested changes from the Octopus Review bot (octopus-review[bot]). Apply the necessary fixes, commit them, and push the updates.
IMPORTANT: Only process review comments authored by octopus-review[bot]. Ignore comments from any other source (CodeRabbit, Greptile, Copilot, human reviewers, etc.).
Rules:
- Ignore false-positive feedback.
- For each false positive, react to the comment with 👎 and explain.
- For each valid and useful suggestion, react to the comment with 👍.
- After fixing a valid issue, reply in the relevant review thread with a brief note describing the fix.
- Resolve the thread/conversation after replying, if resolving is supported.
- If thread resolution is not supported, leave a reply clearly stating that the issue has been addressed.
Once all fixes are applied and pushed, re-trigger an Octopus review of the PR (see Step 6).
Instructions
Follow these steps carefully and in order:
Step 1: Discover Open PRs
- Save the current branch name:
git branch --show-current - List open PRs authored by the current user:
gh pr list --author "@me" --state open --json number,title,headRefName,reviewDecision,url - If no open PRs exist, inform the user and stop.
- Display the list of open PRs with their review status to the user.
Step 2: Check Reviews for Each PR
For each open PR (or a specific PR if the user provided a number as argument $ARGUMENTS):
- Fetch review comments and review threads:
gh pr view <number> --json reviews,reviewRequests,comments,title,headRefName,url gh api repos/{owner}/{repo}/pulls/<number>/comments --jq '.[] | select(.user.login == "octopus-review[bot]") | {id, path, line, body, user: .user.login, created_at}' gh api repos/{owner}/{repo}/pulls/<number>/reviews --jq '.[] | select(.user.login == "octopus-review[bot]") | {id, state, body, user: .user.login}' - Also check for inline review comments (conversation threads):
gh pr view <number> --comments --json comments - Check if the latest Octopus Review bot review has 0 findings:
- Look at the most recent review/comment from
octopus-review[bot] - If the latest bot comment contains "0 findings" (e.g., "5 files reviewed, 0 findings"), this means all previous issues have been resolved
- In this case, skip this PR entirely — there is nothing to fix. Inform the user: "PR #X: Latest review shows 0 findings — all issues resolved, skipping."
- Look at the most recent review/comment from
- Filter for actionable feedback from
octopus-review[bot]only:- Reviews with state
CHANGES_REQUESTED - Unresolved review comments (inline code suggestions, requested changes)
- General PR comments that contain action items
- Reviews with state
- Skip PRs that have no actionable feedback from the bot (state is
APPROVEDor no reviews).
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.
- 11d ago First seen · 133 lines · 63 tokens per session scan A ebfd2a8c5b69
autofix is a skill published in the GitHub repository octopusreview/octopus-plugin (0 stars, last pushed 10d ago), licensed MIT. It adds 63 tokens to every session and 1,452 once invoked, about $0.0003 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 skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.