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 Rockielab/rockie-codex --skill propose-harness-changegit clone --depth 1 https://github.com/Rockielab/rockie-codexWrote 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/rockielab/rockie-codex/propose-harness-change)<a href="https://agentmods.dev/skills/rockielab/rockie-codex/propose-harness-change"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-codex/propose-harness-change/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/rockielab/rockie-codex/propose-harness-change"><img src="https://agentmods.dev/badge/skills/rockielab/rockie-codex/propose-harness-change.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 | $0.00134 | $0.01100 |
| Opus 5.5 | $0.00054 | $0.00440 |
| Sonnet 5.5 | $0.00027 | $0.00220 |
| Haiku 4.5 | $0.00013 | $0.00110 |
Grade A, and why
propose-harness-change 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.
This is a copy
92% identical to propose-harness-change — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/propose-harness-change — safe self-improvement
Autonomous research harnesses that let the agent edit themselves tend to drift (MINJA / eTAMP memory-poisoning, arXiv 2603.29231's finding that "memory scaffolds universally decrease long-horizon reliability", the Ouroboros "AGENTS.md rewrite" footgun). rockie's discipline is Generator / Verifier / Updater separation — nobody is allowed to propose, verify, and commit in the same role.
The three roles
Generator (the proposing agent)
- Writes the diff against a LOCAL CLONE of the rockie source repo.
- Writes a short rationale: what pattern broke, why the fix composes with existing differentiators, what smoke-test assertion(s) prove it.
- Never commits directly. Produces a patch file
~/rockie-proposals/<YYYY-MM-DD-slug>/patch.diffplusrationale.md,test.sh(the specific smoke-test snippet).
Verifier (fresh-context audit agent)
- Dispatched via the
Agenttool with NO prior context. - Reads the patch + rationale, the files being touched, and the
CONTRIBUTING.mdcomposition rules. - Must answer four questions with evidence:
- Does this compose with the existing differentiators, or duplicate one of them?
- Does the smoke test actually test the claimed improvement?
- Is the change local (one file) or does it ripple across the schema?
- Is there a path-traversal, SQL-injection, or shell-injection regression?
- Returns
APPROVE|CHANGES_REQUESTED|REJECTwith a short report.
Updater (the human)
- Reviews Verifier report + diff.
- Runs
bash tests/smoke-test.shin the rockie clone — must be green. - If everything looks right, runs
scripts/apply_upstream_patch.sh <proposal-dir>which commits the diff locally with the rationale as the commit message, then offersgh pr create. - The human — not the agent — chooses when to push.
Invocation
Normal flow (agent finds a harness-level improvement during work):
[LEARN harness-upstream] apply_patch.py should normalize Windows line endings before SEARCH match
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 First seen · 99 lines · 134 tokens per session scan A 124c0809ee38
propose-harness-change is a skill published in the GitHub repository Rockielab/rockie-codex (20 stars, last pushed 12d ago), licensed Apache-2.0. It adds 134 tokens to every session and 1,100 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to propose-harness-change, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…