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 zernie/vigiles --skill debug-my-harnessgit clone --depth 1 https://github.com/zernie/vigilesWrote 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/zernie/vigiles/debug-my-harness)<a href="https://agentmods.dev/skills/zernie/vigiles/debug-my-harness"><img src="https://agentmods.dev/badge/skills/zernie/vigiles/debug-my-harness.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00114 | $0.00825 |
| Opus 5 | $0.00057 | $0.00413 |
| Sonnet 5 | $0.00023 | $0.00165 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
debug-my-harness 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 8d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose harness misbehavior from the flight recorder — the local, append-only ledger
at .vigiles/runs.jsonl that vigiles writes as your harness runs. It records what actually
happened, so you debug from evidence instead of guessing.
What's in the ledger
One JSON record per line, each with a kind:
hook— a compiled-hook gate decision:{event, decision: allow|deny|ask, mode: enforce|observe, rule, cmd, reason}.agent— a subagent tool-contract decision:{name, tool, allowed, reason}(afalse= the agent went outside its lane).skill— a skill activation:{name, fired}.eval— a measured metric:{name, metric, value}(e.g. trigger-rate recall/precision).capability-diff— a blast-radius change:{pr, added, removed, widened}.
Instructions
Step 1: Read the ledger
Read .vigiles/runs.jsonl (JSONL — one record per line; tolerate a torn last line). If it's
absent or empty, say so — there's nothing recorded yet; suggest running the harness (or
vigiles audit) first. Do NOT fabricate records.
Step 2: Answer the specific question, evidence-first
Match the user's question to the ledger:
- "Why did skill X stop firing / why does the wrong one run?" — count
skillfires by name over time. If X's fire-rate dropped, look for a sibling that fired on the same kinds of prompts (a selection collision) and check their descriptions for overlap. Recommend differentiating or merging the descriptions. - "Why didn't my hook block that?" — find
hookrecords for the event. Adecision: allowon something that should be denied, ormode: observe(shadow, never blocks), or the absence of any record, tells you which. Recommend flippingobserve→enforceor fixing the gate logic. - "Did a subagent misbehave?" — list
agentrecords withallowed: false: the agent reached for a tool outside its declared contract. Point at the contract to tighten or widen. - "Is it getting worse?" — compare
evalmetric values (recall/precision) across runs; a downward trend is drift (often after a harness/model upgrade).
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.
- 8d ago First seen · 58 lines · 114 tokens per session scan A 3593437b3383
debug-my-harness is a skill published in the GitHub repository zernie/vigiles (15 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 825 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
dev-doctor
Run a development-focused health check on the AIWG repository structure.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
aiwg-doctor
Run a comprehensive health check on the AIWG installation and workspace with pass/fail diagnostics and remediation steps.
browser-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging: find the cause before writing any fix.