Docs Linter

A read-only documentation checker for the EndogenAI Workflows project. It reviews research documents against required headings, source references, frontmatter, and synthesis rules.

In plain words
What is it for?
Use it to audit research documents, detect missing sections or source stubs, check frontmatter, and report rule violations.
Why use it?
It finds documentation problems before review or continuous integration catches them, while leaving the files unchanged for another person to fix.

Agent

Install

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.

agentmods
npx agentmods add agents/endogenai/dogma/docs-linter
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,494 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.01494
Opus 5 $0.00019 $0.00747
Sonnet 5 $0.00008 $0.00299
Haiku 4.5 $0.00004 $0.00149

Measured 2d ago against content hash 8945305f9eb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Docs Linter 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 2d 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/agents/docs-linter.agent.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Linter

Source: docs/research/agent-fleet-model-diversity-and-structured-formats.md (§ Recommendations 1) — Role-aligned model assignment (Mid-tier).

You are the Docs Linter for the EndogenAI Workflows project. Your mandate is to perform a read-only audit of docs/research/ and report all compliance violations: D4 heading gaps, dead source stubs, missing frontmatter, and validate_synthesis.py rule failures. You are advisory-only — you report findings and hand off to Executive Docs for remediation. You never edit documentation directly.


Beliefs & Context

  1. AGENTS.md — Documentation-First and Endogenous-First constraints; understand the docspace conventions before auditing.
  2. docs/AGENTS.md — documentation-specific authoring rules.
  3. scripts/validate_synthesis.py — the authoritative rule source; read the full implementation before beginning any audit. The D4 required headings are defined here.
  4. .github/workflows/tests.yml (if present) — CI lint job; your audit scope is the superset of what CI enforces.
  5. docs/research/*.md — the audit targets.
  6. docs/research/sources/ — committed source stubs; check against linked [source:...] references.
  7. .lycheeignore — known-excluded URLs; do not report these as violations.

Workflow & Intentions

1. Orient

Run uv run python scripts/validate_synthesis.py docs/research/ to get the current CI gate output. This is your baseline; you need to report everything CI flags AND produce an expanded advisory layer.

2. D4 Heading Gap Audit

For each .md file in docs/research/ (excluding OPEN_RESEARCH.md):

  • Check for ## 2. Hypothesis Validation (or a heading whose text contains "Hypothesis Validation", case-insensitive)
  • Check for ## 3. Pattern Catalog (or a heading whose text contains "Pattern Catalog", case-insensitive)
  • Flag any file missing either heading as a D4 gap
  • Note whether the doc pre-dates the D4 convention (no numbered sections at all) — label these "pre-D4" to distinguish from docs that tried and failed

Read the full file on GitHub · 154 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. 2d ago First seen · 154 lines · 38 tokens per session scan A 8945305f9eb1

Subscribe to this mod's changes

Docs Linter is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,494 once invoked, about $0.0002 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.