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 independent-reviewgit 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/independent-review)<a href="https://agentmods.dev/skills/chocomyong/harness-kit/independent-review"><img src="https://agentmods.dev/badge/skills/chocomyong/harness-kit/independent-review/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/independent-review"><img src="https://agentmods.dev/badge/skills/chocomyong/harness-kit/independent-review.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 | $0.00048 | $0.00318 |
| Opus 5.5 | $0.00019 | $0.00127 |
| Sonnet 5.5 | $0.00010 | $0.00064 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
independent-review 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
Independent review
The author's frame is the blind spot that produced the bug. Review from outside it: ideally a fresh session or a subagent that did not write the change.
Steps
- Read the full diff (
git diff --staged, or the commit range for a loop) and the staged file list. Flag every file the stated goal does not require. - Check against the rules file: the top invariant first, then the commit contract.
- Open the
PATTERNS.mdcards indexed for the touched areas and check the change does not undo a prevention rule. - Check the verification, not just the code. For each claimed "done":
- did the new path actually run, with output shown;
- would the check fail if the change were wrong (was the bug re-injected);
- was it measured in the right place (sample source, overlap with tuning data, real conditions);
- was any verification step simplified away, or a scoring harness left uncommitted.
- Report blocking findings first, each with
file:lineand the concrete failure it causes. Then non-blocking ones. If nothing blocks, say so plainly.
Treat a blocking finding as a required fix before push, not a suggestion.
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 · 27 lines · 48 tokens per session scan A 5eb7a5a15d53
independent-review is a skill published in the GitHub repository chocomyong/harness-kit (2 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 318 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
gentle-ai-rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
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…
debug-issue
Systematically debug issues using graph-powered code navigation.
review-team
Use when assigned a review or when an authored review boundary is reached.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
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…