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 ronaknnathani/relay --skill pr-fixgit clone --depth 1 https://github.com/ronaknnathani/relayWrote 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/ronaknnathani/relay/pr-fix)<a href="https://agentmods.dev/skills/ronaknnathani/relay/pr-fix"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/pr-fix.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.03013 |
| Opus 5 | $0.00038 | $0.01507 |
| Sonnet 5 | $0.00015 | $0.00603 |
| Haiku 4.5 | $0.00008 | $0.00301 |
Grade A, and why
pr-fix 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Fix
Drive a PR to a mergeable state: a green CI, every review comment fixed-and-resolved or
replied-and-flagged, and no merge conflicts with the base. Work the three
fronts — CI, comments, conflicts — and loop until all are clear. Fix root causes, never silence
failures or guess an author's intent. Use review's shared severity vocabulary (Critical / Important /
Suggestion). Run independent investigations as sub-agents when available; otherwise do them inline.
Two modes — check your input first
Delegated mode — a caller supplied a watcher worklist. pr-monitor hands you items taken from a
relay pr watch digest: each carries reason, source, id, answers, updatedAt, body,
thread_id, path, line, and for checks the check_name and check_run_id. That worklist is complete and
authoritative:
- Skip step 1's broad assessment. Do not re-run the PR/comment/thread/check sweep and do not build
a full context bundle — the watcher already observed all of it. Bind
REPOandPRand go straight to the work. - Fetch only what the specific item needs: the failed run's log for a
check_run_id,git log/git blamefor a conflicting hunk, the file under an inline comment. - Fix once, then return — no reassessment loop. The watcher re-observes after your push, and the next attention event carries whatever is left.
- Return a structured result, one entry per supplied item: the item id, what you did,
fixed,replied,escalated, orfailed, and the reason when it is notfixed. Report pushed commits and the new head SHA. - Never run
relay pr watch tickorstatus, and never schedule anything. The caller owns the watcher record.
Direct mode — no worklist was supplied. Assess the PR yourself and loop until clear, exactly as described below. This is the manual path and it is unchanged.
Quick commands
| Task | Command |
|---|---|
| PR + check status | gh pr view --json number,title,state,statusCheckRollup,mergeable |
| CI checks | gh pr checks |
| Failed run logs | gh run view <RUN_ID> --log-failed |
| Inline review comments | gh api "repos/$REPO/pulls/$PR/comments" --jq '.[] | {id,user:.user.login,path,line,body}' |
| Reply to an inline comment | gh api "repos/$REPO/pulls/comments/<ID>/replies" -f body="$BODY" |
| Reply to a conversation comment | gh pr comment "$PR" --body "$BODY" |
| Reply to a review body | gh pr review "$PR" --comment --body "$BODY" |
| Resolve a thread (after fixing) | gh api graphql -f query='mutation($t:ID!){resolveReviewThread(input:{threadId:$t}){thread{isResolved}}}' -F t=<THREAD_ID> |
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 Changed · +75 lines · +18 tokens per session 3e6dcf448e79
- 7d ago First seen · 107 lines · 58 tokens per session scan A 5f44779d80fd
pr-fix is a skill published in the GitHub repository ronaknnathani/relay (3 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 3,013 once invoked, about $0.0004 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
comet-github-issue-fix
A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.
winui-session-report
Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.
chrome-devtools-mcp
Use Chrome DevTools MCP from .NET agents and .NET-focused repos to inspect, debug, and automate Chrome through an MCP client. USE FOR: the repo needs browser-level debugging for ASP.NET Core, Blazor, WebAssembly, or any .NET app with a web UI; the user wants an MCP server that can inspect console. DO NOT USE FOR: pure…
managedcode-orleans-graph
Integrate ManagedCode.Orleans.Graph into an Orleans-based .NET application for grain-call policy enforcement, deadlock detection, live-call telemetry, and Mermaid graph diagnostics. USE FOR: ManagedCode.Orleans.Graph integration; allowed grain transitions; Orleans call filters; live policy graphs; reviewing Orleans…
asynkron-profiler
Use the open-source free Asynkron.Profiler dotnet tool for CLI-first CPU, allocation, exception, contention, and heap profiling of .NET commands or existing trace artifacts. USE FOR: Asynkron.Profiler setup; automation-friendly profiling output; CPU, allocation, exception, contention, and heap investigation. DO NOT…
michel-monitor-pull-request-github-actions
Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment. Invoke whenever Michel's CI monitor loop triggers with anyfailure, stuck, or nottriggered — the bash loop already handles pending and allgreen silently, so…