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 kensaurus/cursor-kenji --skill iterate-agent-harnessgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/iterate-agent-harness)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/iterate-agent-harness"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/iterate-agent-harness/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/kensaurus/cursor-kenji/iterate-agent-harness"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/iterate-agent-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00064 | $0.01633 |
| Opus 5.5 | $0.00026 | $0.00653 |
| Sonnet 5.5 | $0.00013 | $0.00327 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
iterate-agent-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 1mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iterate-agent-harness — Failure → Durable Guard
Degree of freedom: MIXED. Failure-class and smallest fix [HIGH freedom];
guard-fails-before-fix and the report shape [LOW freedom — run exactly].
When an agent run ends wrong, the fix is not just to redo the task — it is to change the harness so the whole class of failure cannot recur silently. This skill converts a single failure into a durable guard plus a regression check.
A failure you cannot reproduce, you cannot prove you fixed. Capture the failure mode, add a guard that fails on it, then make the guard pass with the smallest durable change.
How to reason
- Observe — happened vs should-have; transcript, state file, diff, CI
- Interpret — routing miss, missing guard, or a gate that passed wrongly
- Classify — premature stop / false completion / reward hacking / scope / handoff / context loss
- Guard — add a guard that fails on the unfixed behavior, then the smallest durable fix
Worked example
Observe: agent said complete-everything was done;
.cursor/complete-everything-state.mdstill has 12 unchecked items. Interpret: false completion — no harness stopped the claim. Classify: false completion; gap is an unwired or skippable completion gate. Fix: add a hook test that fails while unchecked items remain; confirm it fails on this tree; then wire the hook. Do not delete the open items to go green.
Self-critique before reporting
- Fail-then-pass — the new guard failed on the unfixed tree
- Class, not incident — the same failure mode would now be caught
- Guard not weakened — passing did not mean deleting or narrowing the check
- Right owner — app bug →
workflow-fix-and-ship; new SKILL.md from scratch →meta-skill-creator
Phase 0 — Capture the failure precisely [HIGH freedom]
- State what happened vs. what should have happened, in one sentence each.
- Classify the failure mode (borrow the taxonomy the toolkit already targets):
- premature stop — quit with actionable work remaining. Shapes to guard: ends the turn with a plan or status report instead of the work; asks a question the repo could answer; stops after a subagent returns without integrating its result; wraps up early believing context is running out (compaction exists — it should not)
- false completion — claimed done without evidence, including fabricated progress: a "ran", "checked", or "verified" with no matching tool result in the transcript
- reward hacking — satisfied the check, not the intent (skipped test,
narrowed assertion,
@ts-ignore, blanket snapshot update) - scope boundary error — treated the plan/visible list as the full scope
- broken handoff — a skill/command/subagent pointed at a missing or wrong target, or a phase transition dropped work
- context loss — forgot earlier state after compaction
- Pull evidence from the agent transcript,
.cursor/*-state.mdfiles,git diff, and CI logs. Link the concrete artifacts.
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.
- 1mo ago Changed · +2 lines · -15 tokens per session 6dfab1a7b26c
- 1mo ago First seen · 136 lines · 79 tokens per session scan A 45042fe2b755
iterate-agent-harness is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 25d ago), licensed MIT. It adds 64 tokens to every session and 1,633 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
testing
Use when writing or reviewing Flutter/Dart tests (unit, widget, golden), fixing flaky tests, adding coverage, or choosing between unit and widget tests.
mockito
Use when generating mocks, stubbing methods, verifying interactions, capturing arguments, or choosing between mocks, fakes, and real objects (Mockito).
mocktail
Use when creating mocks, stubbing methods, verifying interactions, registering fallback values, or choosing between mocks, fakes, and real objects (Mocktail).
component-creation
Step-by-step workflow for creating accessible, tested UI components. Use when the user asks to create a new UI component.
write-unit-tests
Write meaningful unit tests for target code.
coverage-improvement
Systematic workflow for identifying coverage gaps and writing missing tests. Use when coverage is below target or the user asks to improve coverage.