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/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/ronaknnathani/relay/pr-fix"><img src="https://agentmods.dev/badge/skills/ronaknnathani/relay/pr-fix.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 | $0.00076 | $0.03230 |
| Opus 5.5 | $0.00030 | $0.01292 |
| Sonnet 5.5 | $0.00015 | $0.00646 |
| Haiku 4.5 | $0.00008 | $0.00323 |
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 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 — 193 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,ignored_non_actionable, orfailed, and the reason when it is notfixed. Report pushed commits and the new head SHA.ignored_non_actionablemeans no reply, reaction, resolution, or other GitHub mutation was made for that item. - 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.
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 Changed · +11 lines 71b0b94e4d8c
- 1mo ago Changed · +75 lines · +18 tokens per session 3e6dcf448e79
- 1mo 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 3d ago), licensed MIT. It adds 76 tokens to every session and 3,230 once invoked, about $0.0003 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
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
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.
windbg-diagnostic-method
Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation. Not a bug-family-specific triage skill.
windbg-kernel-bugcheck-triage
Use when a kernel dump reports a Windows bugcheck; decode parameters and recover exception or trap context before investigating your driver. Not for user-mode process crashes or blaming a module from its name alone.
windbg-kernel-verifier-triage
Use when a kernel dump contains Driver Verifier violations; inspect flags, bugcheck subcodes, and available I/O shadow state. Not for Application Verifier user-mode stops or inferring a violation from enabled flags alone.