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 agentmods add instructions/dbhq-uk/dovetail-skill/agents-mdgit clone --depth 1 https://github.com/dbhq-uk/dovetail-skillWrote 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/instructions/dbhq-uk/dovetail-skill/agents-md)<a href="https://agentmods.dev/instructions/dbhq-uk/dovetail-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/dbhq-uk/dovetail-skill/agents-md.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 | $0.01377 | $0.01377 |
| Opus 5 | $0.00688 | $0.00688 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
dovetail-skill AGENTS.md 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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and people) working in this repository.
What this is
dovetail - a repository coherence checker for AI coding agents. It follows the Agent Skills layout (skills/<name>/SKILL.md) and ships as a Claude Code plugin.
Layout
.claude-plugin/plugin.json # plugin manifest
skills/dovetail/SKILL.md # the skill: dispatch and the triage loop
skills/dovetail/scripts/ # python, standard library only
skills/dovetail/references/ # the finding contract and one rubric per reviewer
skills/dovetail/ci/ # workflow templates users copy into their own repo
skills/dovetail/tests/ # offline, no model calls
install.sh / install-codex.sh # local symlink installers (Claude / Codex)
docs/design-notes.md # why the tool is shaped this way
The three layers
Layer 1, deterministic - scan.py runs
the graph queries, the exact checks, the convention checks, the git-history
signals and any repo-local plugins. Seconds, no model, no network.
Layer 2, judgement - reviewer.py
holds the roster, tiering and the shared validator;
claimscan.py narrows contradiction
candidates into clusters. Reviewers run as in-session subagents interactively,
or through ci_dispatch.py for the
scheduled job. Rubrics live in skills/dovetail/references/reviewers/, loaded by name
at dispatch time.
Layer 3, triage - entirely in SKILL.md. No
Python TUI: findings are rendered into the session as markdown, which makes the
loop a conversation that can be interrupted and questioned rather than a modal
application.
CI templates: dovetail-pr.yml
(deterministic, gates a merge) and
dovetail-scheduled.yml
(full audit, reports via issue.py, never
gates).
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.
- 6d ago First seen · 87 lines · 1,377 tokens per session scan A 94a9b69303a4
dovetail-skill AGENTS.md is an instructions file published in the GitHub repository dbhq-uk/dovetail-skill (3 stars, last pushed 19d ago), licensed MIT. It adds 1,377 tokens to every session, about $0.0069 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 instructions, from other repositories
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.
sentry-instrumentation AGENTS.md
Instructions for tortastudios/sentry-instrumentation, covering agents guide — sentry-instrumentation, what this repo is, this repo has no "skill registry", if you're a codex agent asked to install this skill and skill-enable block (copy into consumer agents.md).
Cerebro AGENTS.md
Instructions for AgenticFirst/Cerebro, covering cerebro — agent context, read before touching integrations, project layout, conventions a fresh agent would otherwise miss and running locally.
critical-thinking AGENTS.md
Instructions for Johna2an/critical-thinking, covering agents.md, repo map, install (for a user asking "should i install this?"), working in this repo and running an eval round.
hometax-doum AGENTS.md
AGENTS.md instructions for lbiz-partners/hometax-doum, covering claude.md — hometax-doum 개발 규칙 (하네스와 쌍), 규칙 ↔ 강제 장치 and 운용 메모.
powerglide AGENTS.md
Instructions for bkataru/powerglide, covering powerglide agent protocol & integration guide, the ralph loop protocol, termination signals, velocity control and reliable pty execution.