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 skills/perhapsspy/project-legibility/agents-md-editornpx skills add perhapsspy/project-legibility --skill agents-md-editorgit clone --depth 1 https://github.com/perhapsspy/project-legibilityWrote 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/perhapsspy/project-legibility/agents-md-editor)<a href="https://agentmods.dev/skills/perhapsspy/project-legibility/agents-md-editor"><img src="https://agentmods.dev/badge/skills/perhapsspy/project-legibility/agents-md-editor.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 | $0.00085 | $0.00754 |
| Opus 5 | $0.00043 | $0.00377 |
| Sonnet 5 | $0.00017 | $0.00151 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
agents-md-editor 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 4d 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 Editor
Purpose
Keep always-read instruction files small, durable, and action-oriented.
Treat these files as startup instructions for future agent sessions, not as session notes, decision logs, onboarding documents, or general reference documents.
Core Rule
Keep only content that should change agent behavior in future sessions.
Good content usually affects one of these:
- command choice
- safety boundaries
- repository-specific workflow
- where to look before acting
- project-specific conventions not obvious from code or tooling
Classification
For each candidate line, choose one destination:
- Keep: durable behavior rule, safety boundary, workflow rule, or short routing instruction.
- Commands: recurring install, build, test, generation, or validation command agents need during normal work.
- Onboarding: first-run setup, local bootstrap, or human-only environment preparation.
- Reference: architecture, naming, ownership, repo/service boundaries, or durable facts better explained elsewhere.
- Handoff: current state, temporary migration status, next step, open work, blockers, or session-specific context.
- Enforcement: scripts, hooks, CI, tests, linters, type checks, generated checks, or policy already enforced mechanically.
- Remove: duplicate, stale, vague, historical, rejected alternative, decision trace, or meta-commentary.
Use the repository's existing surfaces for non-AGENTS content. Do not invent a new documentation structure unless the user asks.
Editing Rules
- Prefer positive instructions.
- Use negative instructions only for durable safety, security, ownership, or destructive-change boundaries.
- Do not preserve temporary state just because it mattered during the edit.
- Do not record rejected alternatives, reversals, or "we decided not to" history in always-read instruction files.
- Do not restate what tooling already enforces unless agent behavior before tooling runs would otherwise be unsafe.
- Replace detailed reference facts with a short pointer when agents only need to know where to look.
- Keep recurring commands when they are needed for normal agent work.
- Move first-run setup and local environment bootstrap instructions to onboarding or setup surfaces.
- Keep the file short enough to scan before acting.
- Avoid vague rules such as "write clean code", "follow best practices", or "be careful".
What ships with it
1 file 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.
- 4d ago First seen · 87 lines · 85 tokens per session scan A feee3dadecac
agents-md-editor is a skill published in the GitHub repository perhapsspy/project-legibility (5 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 754 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
author
Write a new doc in the right place with the right name. Use when asked to "write a doc", "where should this doc go", "add an ADR", "document this decision", "new spec", or "new feature plan".
router
Find the right doc before reading code. Use when asked "where is X documented", "is there a spec/ADR for X", "what's the roadmap", "open bugs", "read the docs about X", or "share the docs".
changelog
Record shipped work in the monthly changelog (append-only). Use when something ships or when asked "what changed", "add to changelog", "release notes", or "what shipped this month".
init
Set up docflow in a repo with no docs yet: scaffold the docs tree, write docflow.json, add agent guidance. Use when asked to "set up docflow", "initialize docs", "scaffold docs", or "make this repo use docflow".
check
Friendly docflow readiness check: one status, one reason, and the exact next command. Use when asked if docflow is set up, ready, or "what do I do next".
doctor
Read-only docflow diagnosis: scans docs, config, changelog, and links, then recommends init, adopt, or repair. Use when asked "check docs setup", "should I set up docflow", "why is docflow not working", or "doctor".