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 chocomyong/harness-kit --skill absence-checkgit clone --depth 1 https://github.com/chocomyong/harness-kitWrote 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/chocomyong/harness-kit/absence-check)<a href="https://agentmods.dev/skills/chocomyong/harness-kit/absence-check"><img src="https://agentmods.dev/badge/skills/chocomyong/harness-kit/absence-check/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/chocomyong/harness-kit/absence-check"><img src="https://agentmods.dev/badge/skills/chocomyong/harness-kit/absence-check.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 | $0.00052 | $0.00396 |
| Opus 5.5 | $0.00021 | $0.00158 |
| Sonnet 5.5 | $0.00010 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
absence-check 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.
What it actually says
Check an absence claim
Presence is proven by one example. Absence needs an exhaustive check. A wrong "it is gone" hides itself - nothing ever contradicts it - so it costs far more than a wrong "it is here".
Steps
- State the claim exactly: "X does not exist", "X is dead", "there is no backup of X".
- Search beyond the first spelling:
- other names, abbreviations, and casings; the concept, not just the identifier;
- callers through indirection: string-based dispatch, config, cron, schedulers, reflection;
- moved, not deleted:
git log -S '<name>'andgit log --diff-filter=D --name-only; - places your tools do not show: ignored files, other branches, the deployed host, other repos.
- Read past the title. A file named after a retired thing can document live things further down.
- Suspect your instruments. "The dashboard does not show it" is a fact about the dashboard.
- Report one of exactly three verdicts, with every place searched:
- present - with
file:line; - absent - only if the search above was exhaustive;
- could not confirm either way - the honest answer when it was not.
- present - with
If you found an observation gap
A real thing with no visible confirmation is a defect in itself: the next person will make the same misjudgment. Note it, and propose making the thing visible.
Background: harness-kit principles/absence-judgment.md.
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 First seen · 32 lines · 52 tokens per session scan A cc542beec5db
absence-check is a skill published in the GitHub repository chocomyong/harness-kit (2 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 396 once invoked, about $0.0002 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 2026-10-16.
Other skills, from other repositories
openrig-skills
Use when an agent running inside OpenRig needs the right skill or context for fleet recovery, seat handover, new-seat orientation, a watchdog wake, cross-host reach to an agent on another machine, rig packaging, an OpenRig upgrade, systematic debugging, queue triage, or implementation planning; also when the agent…
oversight-team
Use when you are a seat on the oversight pod (a standing monitor-mode rig that keeps OTHER rigs healthy), configuring or running the drift detectors, or choosing whether to intervene vs escalate. Covers the pull-not-poll posture, the v0 detectors (premature-park, process-drift, off-task, token-burn), the intervention…
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
bug-fixer
name: bug-fixer description: Used when the user says "this feature is broken", "getting an error", "something's not right", or reports a bug, compilation error, or runtime exception. Locates root cause through a four-stage systematic debugging process and fixes it. version: 1.2.0 updated: 2026-06-27 requires: [].
reqforge-greenkeeper
name: reqforge-greenkeeper description: Used when maintaining the ReqForge repository itself and its release gates fail — pnpm test, pnpm forge-smoke, pnpm sync:discover, adapter drift, skill fixtures, loadouts, or test-demo golden path. Restores a green, synced state with minimal changes. Not for bugs in user apps…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.