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 roarista/awesome-harness --skill check-allgit clone --depth 1 https://github.com/roarista/awesome-harnessWrote 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/roarista/awesome-harness/check-all)<a href="https://agentmods.dev/skills/roarista/awesome-harness/check-all"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/check-all/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/roarista/awesome-harness/check-all"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/check-all.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 | $0.00084 | $0.00651 |
| Opus 5 | $0.00042 | $0.00326 |
| Sonnet 5 | $0.00017 | $0.00130 |
| Haiku 4.5 | $0.00008 | $0.00065 |
Grade A, and why
check-all 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 10d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
check-all — deterministic readiness gate
Step 6 of THE PROCEDURE (
~/.codex/AGENTS.md), the deterministic half. It costs no tokens and cannot be fooled by intent — run it rather than asserting the code works.
Invocation
bash ~/.codex/tools/check-all/check_all.sh [REPO_DIR] [--fast] [--json]
REPO_DIR— repo root (default: current directory)--fast— skip tests (still runs lint/typecheck/file-size/TODO)--json— machine-readable output instead of the table
Checks
| Check | Type | Default | Notes |
|---|---|---|---|
| base-gate | HARD | fail | Composes the repo's own scripts (factory:check → ci:safe → lint/typecheck); falls back to tsc/ruff/mypy |
| file-size | soft | warn | Flags source files > 800 lines |
| no-TODO | soft | warn | TODO/FIXME/XXX in source files |
| dup-code | soft | warn | jscpd if available, else skipped |
| semgrep | soft | warn | ADVISORY only — prints findings, never fails the gate. SEMGREP_STRICT=1 makes it blocking. Silent skip if semgrep is not on PATH |
| tests | HARD | fail | Skipped under --fast; runs npm test / pytest -q |
Hard check fails → OVERALL FAIL → exit 1. Soft checks warn and exit 0 unless configured to fail.
Exit codes: 0 all hard checks passed; 1 a hard check failed or a "fail"-severity soft check tripped.
Optional per-repo config: .check-all.json
{
"base_command": "npm run factory:check",
"max_file_lines": 500,
"todo_severity": "fail",
"filesize_severity": "warn",
"skip_tests": false,
"src_globs": ["src/**/*.ts", "lib/**/*.py"]
}
All keys optional; absent file means all defaults apply.
Rules
- Report the gate's real output. Never summarize a run you did not perform, and never call a change ready on a failing hard check.
- Use
--fastfor a mid-work sanity pass; run the full gate before the close (compact-prep). - If the script is missing, the harness was not installed for Codex: run
./install.sh --codexfrom the awesome-harness repo.
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.
- 10d ago First seen · 55 lines · 84 tokens per session scan A 49a877bd7ca9
check-all is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 15d ago), licensed MIT. It adds 84 tokens to every session and 651 once invoked, about $0.0004 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.