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 stilero/claude-plugins --skill fix-pr-comments-loop-roundgit clone --depth 1 https://github.com/stilero/claude-pluginsWrote 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/stilero/claude-plugins/fix-pr-comments-loop-round)<a href="https://agentmods.dev/skills/stilero/claude-plugins/fix-pr-comments-loop-round"><img src="https://agentmods.dev/badge/skills/stilero/claude-plugins/fix-pr-comments-loop-round/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/stilero/claude-plugins/fix-pr-comments-loop-round"><img src="https://agentmods.dev/badge/skills/stilero/claude-plugins/fix-pr-comments-loop-round.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 | $0.00167 | $0.12438 |
| Opus 5.5 | $0.00067 | $0.04975 |
| Sonnet 5.5 | $0.00033 | $0.02488 |
| Haiku 4.5 | $0.00017 | $0.01244 |
Grade A, and why
fix-pr-comments-loop-round 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 — 567 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fix-pr-comments-loop-round
Per-round executor for the fix-pr-comments-loop orchestrator. The orchestrator dispatches one fresh Agent-tool subagent per round, the subagent loads this skill, runs steps 0–8 against the supplied prompt args, and emits a single fenced ```json block as the last thing in its output so the orchestrator can parse the round's outcome and decide whether to loop, exit clean, or bail.
This skill does not re-implement the fix logic or the hardcore review logic. It orchestrates the existing skills pr-comment-fixer:fix-issues and hardcore-code-reviewer:hardcore-code-reviewer within a single round.
Prompt args (supplied by orchestrator)
The orchestrator passes the following values via the Agent-tool prompt body. The subagent does NOT re-derive them and does NOT re-validate the open-PR / clean-working-tree preconditions — the orchestrator already did. Reading the orchestrator-supplied args as-is is the contract.
Required:
ROUND— the current round number (1-based integer). Drives the[round N/<cap>]status prefix and the deterministic round commit message in step 4.OUTER_CAP— the configured outer-round cap (default 8). Used purely for the[round N/<cap>]status prefix; the subagent does not enforce the cap itself (that lives in the orchestrator).OWNER,REPO,PR_NUMBER— used in everygh api graphql -F owner=$OWNER -F repo=$REPO -F pr=$PR_NUMBER ...call below.BASE_BRANCH— used in step 5'sgit merge-base "origin/$BASE_BRANCH" HEADfor the mapping-rule diff.COPILOT_REVIEWER— the resolved reviewer login (already de-@-prefixed by the orchestrator; e.g.copilot-pull-request-reviewer). Used in step 6'sgh pr edit "$PR_NUMBER" --add-reviewer "$COPILOT_REVIEWER".VERIFY_CMD— the verification command string the orchestrator resolved at run start (e.g.npm run build && npm test && npm run lint,pytest && ruff check .,make test, or an explicit override). The subagent runs this verbatim in step 3.INNER_ITERATION_CAP— default3. Cap on hardcore-review iterations within this round (step 2).POLL_CAP_MINUTES— default60. Cap on copilot polling duration within this round (step 7).POLL_INTERVAL_SECONDS— default60. Interval between polling attempts.COMPLEXITY_THRESHOLD— default3. Max number of files (in the unionFIX_FILES ∪ INNER_FIX_FILES) unrelated to the original comment's file before the round bails to the user.RESOLVE_WINDOW— default20. Half-window size (lines on each side) for the strict mapping rule in step 5.
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 · 567 lines · 167 tokens per session scan A 789e7d749e53
fix-pr-comments-loop-round is a skill published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 167 tokens to every session and 12,438 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…