dogma: Skill for Claude Code

.github/skills/agent-file-authoring/SKILL.md

agent-file-authoring is a skill for Claude Code from EndogenAI/dogma. It costs 120 tokens per session (2,948 once invoked), scanned A, original, Apache-2.0.

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

In plain words
What is it for?
Use it when adding or modifying custom agent definitions and when diagnosing validation failures for those files.
Why use it?
It helps these role files meet required formatting, naming, cross-reference, and automated validation checks.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions AGENTS.md.

This is EndogenAI/dogma's own configuration. It tells Claude Code how to work on dogma itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dogma configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/scaffold_agent.py <role-slug>.

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.

agentmods badge for agent-file-authoring

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.

agentmods 80×15 button for agent-file-authoring

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.02948
Opus 5 $0.00060 $0.01474
Sonnet 5 $0.00024 $0.00590
Haiku 4.5 $0.00012 $0.00295

Measured 8d ago against content hash 5a339224db54, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

  1. 8d 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 15d ago), licensed Apache-2.0. It adds 120 tokens to every session and 2,948 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

air-blackbox-sales-agent

AIR Blackbox's autonomous sales prospecting agent. Finds Python AI projects on GitHub that need EU AI Act compliance, identifies the right person to contact (CEO, CTO, lead maintainer), runs a free compliance scan, and drafts personalized outreach emails that convert to engagement. The sales flow: free scan as the…

airblackbox/airblackbox · 248 tokens

interpret-results

Interprets AIR Blackbox scan results and maps findings to specific EU AI Act articles, recitals, and remediation steps. Use when the user has scan output and wants to understand what to fix, why it matters, or how to prioritize.

airblackbox/airblackbox · 49 tokens

compliance-scan

Scans a Python AI project for EU AI Act compliance gaps using AIR Blackbox. Use when the user asks to check compliance, scan their code, audit their AI project, or mentions EU AI Act, Articles 9-15, or compliance checking.

airblackbox/airblackbox · 51 tokens

nio-external-score

Nio external scoring-endpoint snapshot. Use when the user asks about their current Nio/risk scores from configured external scoring endpoints — e.g. "what's my Nio score", "tell me the nio score", "check my external/guardrail endpoint scores", "what do my scoring services return right now", "list the current risk…

core0-io/nio · 97 tokens

nio-scan

Nio code/skill execution-risk scanner. Use when the user wants to scan a file, repo, directory, or skill for execution risks — e.g. "scan this code for risks", "is this file/plugin dangerous", "check this repo for malicious code", "run nio scan on ". Focused single-purpose skill; for other Nio operations use /nio.

core0-io/nio · 81 tokens

constitutional-ai

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

synthetic-sciences/openscience · 58 tokens