documentation

Three concerns, one persona: JSDoc on code exports, Markdown docs that describe the code, and the cross-references that knit them together. When the diff changes what the code does, the docs that describe it must keep up; when the diff renames or moves a file, every pointer to it must be updated; when the spec changes…

Agent for Codex

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/morpho-org/sdks/documentation
Clone the repo
git clone --depth 1 https://github.com/morpho-org/sdks

Made for: Codex.

Per session 1 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,069 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 $0.00001 $0.02069
Opus 5 $0.00000 $0.01035
Sonnet 5 $0.00000 $0.00414
Haiku 4.5 $0.00000 $0.00207

Measured yesterday against content hash fd47fbff6cab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation 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 yesterday.

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.

.agents/pr-review-engine/agents/documentation.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Analyzer

Three concerns, one persona: JSDoc on code exports, Markdown docs that describe the code, and the cross-references that knit them together. When the diff changes what the code does, the docs that describe it must keep up; when the diff renames or moves a file, every pointer to it must be updated; when the spec changes a rule, the persona that enforces it must reflect the new rule.

1. JSDoc on exported symbols

Focus: JSDoc/TSDoc on public APIs and types in packages/<pkg>/src/index.ts and the files it re-exports.

Canonical JSDoc rules: docs/jsdoc-style.md (operationalizes AGENTS.md §6 and MISSION.md goal #3 — AI-legibility). Read it at run time and use its checklist as the rubric.

Prompt must include:

  • The docs/jsdoc-style.md checklist (what needs JSDoc, what does not, the required block order, @param / @returns / @throws / @example rules, error-message phrasing).
  • New or modified public exports re-exported from packages/<pkg>/src/index.ts must have JSDoc that conforms to docs/jsdoc-style.md.
  • Doc comments accurate vs. the implementation (no stale references to renamed args, removed return values, changed throw behavior).
  • Public types use semantic names — flag generic T, U, Foo where domain names exist.
  • @example blocks compile and follow the runnable-recipe shape from the style guide.

2. Markdown documentation accuracy

When the diff touches code, the Markdown docs that describe that code may be drifting. When the diff touches Markdown, the code it describes may no longer match. Either direction is a finding.

Files in scope (read each one whose content is in the diff OR which references something that the diff changed):

  • README.md (root and per-package).
  • AGENTS.md (root and per-package). CLAUDE.md is a symlink to AGENTS.md — don't double-check.
  • MISSION.md, CONTRIBUTING.md, SECURITY.md.
  • docs/**/*.md (style guides, architecture deep-dives, TIBs, templates).
  • .agents/pr-review-engine/SKILL.md, .agents/pr-review-engine/agents/*.md, .agents/pr-review-engine/references/*.md, .agents/commands/*.md.
  • Any *.md colocated with a package (packages/<pkg>/*.md).

Read the full file on GitHub · 104 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. yesterday First seen · 104 lines · 1 tokens per session scan A fd47fbff6cab

Subscribe to this mod's changes

documentation is an agent published in the GitHub repository morpho-org/sdks (40 stars, last pushed yesterday), licensed MIT. It adds 1 tokens to every session and 2,069 once invoked, about $0.0000 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 2026-09-01.