What is harness-intel?

A read-only review tool for a coding project's instructions, notes, and agent setup. It has an audit mode for finding differences between those instructions and the actual code, and a scouting mode for proposing useful automation ideas.

Use it to audit one repository for documentation or behavior drift, or to identify repeated work from transcripts and research possible additions to the coding workflow.

It helps reveal when a project's documented workflow no longer matches its code or when repeated work could be automated. It requires evidence for findings and does not change files.

harness-intel — Skill for Claude Code and Codex by roarista

Install

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.

Any agent

npx skills add roarista/awesome-harness --skill harness-intel

Clone the repo

git clone --depth 1 https://github.com/roarista/awesome-harness

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/roarista/awesome-harness/harness-intel/github.svg)](https://agentmods.dev/skills/roarista/awesome-harness/harness-intel)

Your own site

<a href="https://agentmods.dev/skills/roarista/awesome-harness/harness-intel"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/harness-intel/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/roarista/awesome-harness/harness-intel"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/harness-intel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,139 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00038	$0.02139
Opus 5.5	$0.00015	$0.00856
Sonnet 5.5	$0.00008	$0.00428
Haiku 4.5	$0.00004	$0.00214

Measured 1mo ago against content hash e2d1de814f22, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harness-intel 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.

skills/harness-intel/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

harness-intel — audit (inward) + scout (outward), proposal-only

Two directions, one discipline: evidence-cited, proposal-only, fit-filtered, never edits the live tree. AUDIT asks "does the harness do what it says?" (fidelity + behavioral drift) for ONE named repo. SCOUT asks "what should we add?" — either by turning Ro's repeated toil into a skill/hook, or stealing an external idea. Pick the mode from Ro's phrasing; if ambiguous, ask.

Hard rules (both modes, non-negotiable)

Proposal-only. Never edit the target repo, or any repo. AUDIT output -> ~/Downloads/HARNESS_DRIFT_<repo>_<date>.md. SCOUT output -> ~/Downloads/HARNESS_SCOUT_<date>.md. Ro reviews; a normal session applies/builds later.
One cheap read-only agent at a time (low-CPU, no VM — [[feedback-low-cpu-no-vm]]). Don't fan out N agents. Kill worker process trees on finish.
Evidence or it didn't happen (R1). Every finding cites file:line / transcript / URL+date / command output read THIS run. Unverifiable -> UNKNOWN, never guessed.
Don't race live sessions. Reading is fine; never write, branch, push, or run ml compact/prune against a repo whose loop may be appending. Note if the tree is dirty.
Fit-filter every idea against OUR constraints (SCOUT) / every fix against real evidence (AUDIT) — no hype, no ungrounded brainstorm. We run API models (Claude/Codex 5.5), low-CPU no-VM no-GPU hardware, ambient hooks+skills not a framework. An idea needing GPU/weights/server/heavy runtime is NON-FIT, say so. A fix with no cited drift/bad-behavior is speculation, capped at 3 bullets in a fenced ## Out-of-scope observations (speculative) section, never in the findings table.

Mode A — AUDIT (inward: one repo vs reality)

Inputs: target repo path (resolve nicknames: intrn -> ~/Downloads/intrn; Vividlist/Previz -> ~/Downloads/Vividlist; forclosurehomes -> ~/Downloads/forclosurehomes; virality -> ~/Downloads/virality-pipeline). Cross-repo baseline: ~/.claude/projects/-Users-rodrigoarista/memory/global_orchestration_rules.md.

Read the full file on GitHub · 63 lines

Changes

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 · +4 lines · -127 tokens per session e2d1de814f22
2mo ago First seen · 59 lines · 165 tokens per session scan A ecf350b2c70e

Subscribe to this mod's changes

harness-intel is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 2,139 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 2026-08-31.

Building agents Debugging

harness-intel next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harness-intelroarista/awesome-harness	Skill	1	4d ago	MIT	A	38	Claude Code, Codex
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	today	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	319	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	today	Apache-2.0	A	15	Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex
loop-engineeringhuytieu/COG-second-brain	Skill	1.3k	15d ago	MIT	A	63	Claude Code