Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/joymin5655/Agentnpx agentmods add skills/joymin5655/agent/harness-auditWrote 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/joymin5655/agent/harness-audit)<a href="https://agentmods.dev/skills/joymin5655/agent/harness-audit"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/harness-audit.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 | $0.00105 | $0.02229 |
| Opus 5 | $0.00053 | $0.01115 |
| Sonnet 5 | $0.00021 | $0.00446 |
| Haiku 4.5 | $0.00011 | $0.00223 |
Grade A, and why
harness-audit 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 6d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/harness-audit
Goal
Produce one interpreted health report of the harness in a single read-only
dry-run. The machine integrity layer (P1-1 doc-reality.sh, the CI jobs, and the
verify-all.sh runner) is the enforcement; this skill is the consumer that
runs it once, reads off a per-check pass/fail table, and turns each failure into a
diagnosis a maintainer can act on.
Concretely the report answers three questions with evidence:
- Is the harness passing its own gates right now? — a per-check PASS / FAIL /
SKIP table, taken verbatim from
verify-all.sh. - What does the doc-reality gate (P1-1) say? — cited explicitly, because it is the gate that catches the harness lying about itself (phantom paths + drifted counts), and it is the one item most easily missed in a wall of green.
- For every non-PASS: why, and what next? — the check's purpose, the likely root cause, the recommended fix, and whether it warrants a new backlog row.
This skill supplies the interpretation; it does not re-implement any check.
The checks live in core/tests/ and CI; here you run them and read the results.
Why this is a layer, not a duplicate of P1-1
P1-1 (core/tests/doc-reality.sh) is a machine gate: it runs in CI, exits 0/1,
and mechanically blocks doc drift. This skill is the agent consumer that sits on
top of that gate — it invokes the whole machine layer in one dry-run and interprets
the results (root-cause, fix, backlog follow-up) the way a maintainer would. It reads
doc-reality's verdict; it never re-derives phantom-path or count logic. Deleting this
skill would not weaken any gate (CI still enforces them); deleting doc-reality would.
That asymmetry is the layer relationship: the gate enforces, the audit interprets.
This mirrors the machine-gate-vs-agent-consumer split the plan draws for H-2.
Steps
1. Run the machine integrity layer (one dry-run)
bash core/tests/verify-all.sh
verify-all.sh is the single-command runner. It dynamically discovers every
core/tests/*.sh check (the runner and its own self-test aside, to avoid recursion —
that self-test runs as its own CI step) so no harness check is silently omitted, and
runs, per check, PASS / FAIL / loud SKIP with a final tally. Its discovered set
already includes the machine layer this audit reports on:
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.
- 6d ago First seen · 170 lines · 105 tokens per session scan A 701683c8b989
harness-audit is a skill published in the GitHub repository joymin5655/Agent (2 stars, last pushed 4d ago), licensed MIT. It adds 105 tokens to every session and 2,229 once invoked, about $0.0005 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
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
background-watch-hook
Use vibe watch to run a managed Harness waiter that returns to the same conversation later. Best for reviews, CI, files, logs, and other wait-now-continue-later workflows.
use-avibe-harness
Use Avibe Harness for durable Agent delegation, Sessions, scheduled Tasks, Watches, Runs, queues, and work that must continue beyond the current turn.
use-show-pages
Build, inspect, update, or share an Avibe Show Page when a visual explanation, diagram, dashboard, report, or interactive prototype would materially help.
use-avibe-vault
Use Avibe Vault for API keys, tokens, passwords, protected credentials, authenticated HTTP requests, or digest signing without exposing secret values to the agent.
technocore-chat
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…