gofer-documentation

gofer-documentation is a skill for Claude Code from eai-support/eai-gofer. It costs 46 tokens per session (873 once invoked), scanned A, original, Apache-2.0.

A documentation skill for Gofer workspaces that writes customer-facing Markdown and creates a diagram showing where documented information comes from.

In plain words
What is it for?
Use it for requirements, architecture notes, decisions, plans, validation evidence, and documentation lineage diagrams.
Why use it?
It helps keep delivery documents understandable and ensures the saved diagram does not expose internal services or infrastructure.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .specify/scripts/node/render-delivery-lineage.mjs \.

Part of the eai-gofer plugin — 4 skills, 28 commands, 42 agents, 3 hooks, 1 MCP server shipped together

Good fit Use it for requirements, architecture notes, decisions, plans, validation evidence, and documentation lineage diagrams.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/eai-support/eai-gofer
agentmods
npx agentmods add skills/eai-support/eai-gofer/gofer-documentation

Made for: Claude Code.

Or install eai-gofer, the plugin that ships this one along with the rest of its 4 skills, 28 commands, 42 agents, 3 hooks, 1 MCP server.

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 gofer-documentation

README.md
[![agentmods](https://agentmods.dev/badge/skills/eai-support/eai-gofer/gofer-documentation.svg)](https://agentmods.dev/skills/eai-support/eai-gofer/gofer-documentation)
Your own site
<a href="https://agentmods.dev/skills/eai-support/eai-gofer/gofer-documentation"><img src="https://agentmods.dev/badge/skills/eai-support/eai-gofer/gofer-documentation.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 873 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 $0.00046 $0.00873
Opus 5 $0.00023 $0.00436
Sonnet 5 $0.00009 $0.00175
Haiku 4.5 $0.00005 $0.00087

Measured 7d ago against content hash 3fe1e8c4c147, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gofer-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 7d 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.

.agents/skills/gofer-documentation/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gofer Documentation And Lineage

Use this skill whenever an agent creates or changes delivery documentation in a Gofer workspace. The durable outputs are human-readable Markdown plus .specify/specs/{feature}/delivery-lineage.json.

Trust Boundary

Gofer is customer-side. Read .specify/references/delivery-lineage.md before writing and enforce all of its export rules.

  • Use plane: customer.
  • Stop EAI dependencies at a public-api-capability node from PublicAPI.
  • Never name or link internal EAI services, repositories, policies, infrastructure, tech-docs, or personal absolute paths.
  • Do not create an internal graph and rely on a viewer filter. The persisted graph itself must be safe for the customer.
  • Record concise rationale and evidence, never hidden chain-of-thought.

Write The Markdown

  1. Preserve the repository's existing documentation conventions. For a new durable document, use frontmatter with a stable doc_id, title, status, owners, and updated date.
  2. Keep the stable doc_id when the title or path changes. Mark replaced documents superseded and link their replacement.
  3. Use descriptive headings so graph sources can point to exact anchors.
  4. Separate requirements, decisions, considered options, concise rationale, acceptance evidence, and outcomes. Do not present a plan as delivered fact.
  5. Use repository-relative links and paths. Include a Git commit and SHA-256 content hash in lineage sources when known.

Record The Selected Decision

Use one explicit heading for each material outcome so the viewer can separate the accepted path from alternatives:

  • ## Selected Approach, ## Approved Direction, ## Chosen Option, or ## Architecture Decision for an accepted choice;
  • ## Rejected Alternative or ## Declined Option for an option not taken;
  • ## Superseded Decision when a later choice replaced it.

State the decision itself in the first paragraph below the heading. Keep the concise rationale and consequences below it. The viewer records the heading as an anchored decision node, shows the latest current accepted decision as the Final selected decision, and highlights the current customer delivery path while fading rejected, superseded, or unhealthy evidence.

Read the full file on GitHub · 94 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. 7d ago First seen · 94 lines · 46 tokens per session scan A 3fe1e8c4c147

Subscribe to this mod's changes

gofer-documentation is a skill published in the GitHub repository eai-support/eai-gofer (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 873 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.

Related

Other skills, from other repositories