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 tatargabor/set-copilot --skill set-repairgit clone --depth 1 https://github.com/tatargabor/set-copilotWrote 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/tatargabor/set-copilot/set-repair)<a href="https://agentmods.dev/skills/tatargabor/set-copilot/set-repair"><img src="https://agentmods.dev/badge/skills/tatargabor/set-copilot/set-repair/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/tatargabor/set-copilot/set-repair"><img src="https://agentmods.dev/badge/skills/tatargabor/set-copilot/set-repair.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 | $0.00034 | $0.01566 |
| Opus 5.5 | $0.00014 | $0.00626 |
| Sonnet 5.5 | $0.00007 | $0.00313 |
| Haiku 4.5 | $0.00003 | $0.00157 |
Grade A, and why
set-repair 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
set-repair — runtime state check
doctor probes the audio chain (binary → device → bytes → signal). This inspects
runtime state: what the PID files, transcripts and wall claims in this project's runtime
dirs say, and whether they are telling the truth. The two do not overlap; run whichever
matches the symptom.
It ends by handing off: anything about a transcript's content belongs to
/transcript-recover.
Rules that apply to everything below
- Check liveness before calling any claim stale. A PID file means nothing until you have
probed the process (
kill -0 <pid>— signal 0 tests reachability without signalling). A dir with a running capture or wall is in use: report it and leave it alone. - Fix only through existing paths. An unconsumed transcript is handed over by
set-copilot stop, never by moving the file yourself — the singlerenameSyncin the handover is the source of truth for "handed over exactly once", and a hand-made copy would break it. Never rotate a live wall's event log;wall --resetexists and checks first. - Report anything destructive, never run it. Print the exact command and let the operator
decide. This includes deleting a PID file, rotating a log, and re-stitching with
--force. - A clean project reports clean. Do not invent work.
Phase 1 — enumerate
ls -d .set/copilot/*/ 2>/dev/null # per-session runtime dirs
ls -d /tmp/set-copilot 2>/dev/null # the unscoped global dir, if it was ever used
For each dir, look at: capture.pid, capture.output, transcript.jsonl /
dictation.jsonl (live names), the *-<timestamp>.jsonl archives, wall.pid,
wall-events.jsonl, mirror.pid, and whether each archive has a .md + -stitched.jsonl
beside it.
Phase 2 — the five faults
First, the cheap census of recordings that never reached the repo (it reads and hashes, writes
nothing): npx set-copilot backfill --dry-run. Anything it lists is saved by
npx set-copilot backfill — through the project's hand-off command for that kind, or into
docs/inputs/copilot/ — which copies and never moves, so it does not touch the "handed over
exactly once" invariant below. Report the command; it writes files into the work tree.
Recordings marked kept back are deliberate, not a fault: the built-in target stands down on a
repo with a public-host remote, and the fix is the repo-visibility.json private mark or
copilot.defaultHandover — never a hand copy into docs/inputs/copilot/.
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 · +9 lines 46567bdfe968
- 1mo ago First seen · 112 lines · 34 tokens per session scan A 82fff076cb7b
set-repair is a skill published in the GitHub repository tatargabor/set-copilot (3 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 1,566 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.