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 cilidinezy-commits/doc-harness --skill skillgit clone --depth 1 https://github.com/cilidinezy-commits/doc-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/cilidinezy-commits/doc-harness/skill)<a href="https://agentmods.dev/skills/cilidinezy-commits/doc-harness/skill"><img src="https://agentmods.dev/badge/skills/cilidinezy-commits/doc-harness/skill.svg" alt="Measured on agentmods" 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 | $0.00178 | $0.01811 |
| Opus 5 | $0.00089 | $0.00905 |
| Sonnet 5 | $0.00036 | $0.00362 |
| Haiku 4.5 | $0.00018 | $0.00181 |
Grade A, and why
doc-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 7d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Harness — Document-Based Project Control
Doc Harness is a documentation system that enables any AI agent or human collaborator to understand and resume project work purely from reading files — no external memory needed.
It creates and maintains five documents per project:
- CLAUDE.md — Project entry point (overview, recovery chain, iron rules, operational rules)
- CURRENT_STATUS.md — Active state (tire tracks / car body / headlights / driving manual)
- FILE_INDEX.md — File catalog organized by category
- WORKLOG.md — Permanent work history (append-only)
- DOC_HARNESS_SPEC.md — Complete specification (reference document)
Two optional documents may be added when a project accumulates such content (see spec.md Chapter 13):
- PARKING_LOT.md — Deferred items with preconditions for revival
- PHILOSOPHY.md — Principles forged by this project's practice
One optional mechanism may be adopted when a project coordinates with others (see spec.md Chapter 14):
- Inter-project inbox/outbox — self-contained file-based messaging protocol.
inbox/andoutbox/directories; YAML-frontmatter Markdown messages; lifecycleunread → read → actioned. Fully described inside doc-harness itself; no external spec needed.
Commands
/doc-harness init [project-name] [description]
Initialize Doc Harness for a new project. Creates all 5 files in the current directory.
→ See init.md for full instructions and templates.
/doc-harness check
Audit the current project's documentation health and reflect on working principles.
→ See check.md for full check procedures.
/doc-harness sync [--auto]
Synchronize status documents with reality. Repair drift, refresh stale fields, register missing files, and optionally trigger phase transition or WORKLOG archival.
interactive(default): Ask before phase transitions, archival, or creating new principle documents.auto: Execute fixes without asking.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 108 lines · 178 tokens per session scan A d22ef262f704
doc-harness is a skill published in the GitHub repository cilidinezy-commits/doc-harness (4 stars, last pushed 6d ago), licensed MIT. It adds 178 tokens to every session and 1,811 once invoked, about $0.0009 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
state
Use when the user says 'update state', 'project state', 'where was I', or at session start to load current context.
harness-step3-session-management
A project setup for keeping an agent’s work state in files between separate chat sessions. It creates a task list, a progress summary, and a script for checking the project environment.
project-context-loader
Load relevant memory, decisions and contacts for the current project at the start of a session.
sweep-now
Run the three read-mostly vault sweeps for stale tracker items, dormant-note candidates, and broken wikilinks, then append one dated result to SWEEPLOG.md.
operator-setup
The AIgent first-run operator-business interview. Learn the operator's business in three plain questions, write the first memory, and play back a briefing that reads personal, not templated. This is the "it remembers me" moment. A distinct skill that LAYERS ON TOP of the base /setup (which is left intact), it does not…
continue
Use when you need the Codex Copilot equivalent of Claude Copilot /continue: resume paused or previous work from tc tasks, work products, memory, and stream context.