What is agent-file-authoring?

A set of rules for creating and editing .agent.md files, which define custom coding-agent roles in a GitHub agents directory.

Use it when adding or modifying custom agent definitions and when diagnosing validation failures for those files.

It helps these role files meet required formatting, naming, cross-reference, and automated validation checks.

How EndogenAI/dogma configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to EndogenAI/dogma. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/EndogenAI/dogma/main/.github/skills/agent-file-authoring/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/EndogenAI/dogma

Made for: Claude Code.

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/endogenai/dogma/agent-file-authoring/github.svg)](https://agentmods.dev/skills/endogenai/dogma/agent-file-authoring)

Your own site

<a href="https://agentmods.dev/skills/endogenai/dogma/agent-file-authoring"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/agent-file-authoring/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/endogenai/dogma/agent-file-authoring"><img src="https://agentmods.dev/badge/skills/endogenai/dogma/agent-file-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,948 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	$0.00120	$0.02948
Opus 5.5	$0.00048	$0.01179
Sonnet 5.5	$0.00024	$0.00590
Haiku 4.5	$0.00012	$0.00295

Measured 2mo ago against content hash 5a339224db54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-file-authoring 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 2mo 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.

.github/skills/agent-file-authoring/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent File Authoring

This skill enacts the Endogenous-First axiom from MANIFESTO.md: agent files are re-encodings of AGENTS.md, not independent inventions. Every .agent.md file derives its structure, posture, and governing constraints from AGENTS.md and MANIFESTO.md. Agents re-encode; they do not re-derive. Full authoring guidance is in docs/guides/agents.md and the fleet catalog in .github/agents/README.md.

1. File Naming and Location

Location: .github/agents/<role-slug>.agent.md
Slug format: kebab-case, lowercase, e.g. executive-docs, research-scout
One file per agent role — do not combine multiple personas into a single file

Use the scaffold helper to generate a compliant template:

uv run python scripts/scaffold_agent.py <role-slug>
# Creates: .github/agents/<role-slug>.agent.md

2. YAML Frontmatter

Every agent file must open with YAML frontmatter:

---
name: <role name in title case>
description: |
  <≥25 character description — CI enforces minimum length>
---

Field requirements (enforced by validate_agent_files.py):

Field	Required	Constraint
`name`	Yes	Non-empty string
`description`	Yes	≥ 25 characters

The description field should be a | block for multi-line content. It is consumed by VS Code and GitHub Copilot as the agent's self-description in selection menus.

2b. Optional Discipline Fields for Project Governance

Every agent file should include optional frontmatter fields to track project governance and effort:

---
name: Executive PM
description: Maintain issues, labels, milestones, and project hygiene...

# Optional — encode project governance, milestone tracking, and effort
tier: Wave 1                    # Milestone this agent targets/belongs to (Foundation|Wave 1|Wave 2|Adoption|Hardening)
effort: M                       # Effort to implement: s/m/l/xl (small/medium/large/xlarge)
status: active                  # Current status: active | beta | deprecated | blocked
area: agents                    # Codebase domain: agents | scripts | docs | ci | tests | deps | research
depends-on:                     # Other agents this agent requires/follows from
  - Review
  - GitHub
---

Read the full file on GitHub · 253 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.

2mo ago First seen · 253 lines · 120 tokens per session scan A 5a339224db54

Subscribe to this mod's changes

agent-file-authoring is a skill published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 120 tokens to every session and 2,948 once invoked, about $0.0005 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.

AI Safety Building agents agent agents-md ai ai-governance ai-harness

agent-file-authoring next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-file-authoringEndogenAI/dogma	Skill	2	2mo ago	Apache-2.0	A	120	Claude Code
custom-brand-designKbWen/agentic-os	Skill	227	4d ago	MIT	A	23	Claude Code, Codex
air-blackbox-sales-agentairblackbox/airblackbox	Skill	25	4d ago	Apache-2.0	A	248	Claude Code, Codex
interpret-resultsairblackbox/airblackbox	Skill	25	4d ago	Apache-2.0	A	49	Claude Code
nio-external-scorecore0-io/nio	Skill	20	13d ago	Apache-2.0	A	97	Claude Code
nio-scancore0-io/nio	Skill	20	13d ago	Apache-2.0	A	81	Claude Code
constitutional-aisynthetic-sciences/openscience	Skill	4.3k	2d ago	Apache-2.0	A	58	Claude Code, Codex

dogma: Skill for Claude Code