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.
git clone --depth 1 https://github.com/eai-support/eai-gofernpx agentmods add skills/eai-support/eai-gofer/gofer-documentationWrote 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.
[](https://agentmods.dev/skills/eai-support/eai-gofer/gofer-documentation)<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>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 | $0.00046 | $0.00873 |
| Opus 5 | $0.00023 | $0.00436 |
| Sonnet 5 | $0.00009 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00087 |
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.
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-capabilitynode fromPublicAPI. - 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
- Preserve the repository's existing documentation conventions. For a new
durable document, use frontmatter with a stable
doc_id,title,status,owners, andupdateddate. - Keep the stable
doc_idwhen the title or path changes. Mark replaced documentssupersededand link their replacement. - Use descriptive headings so graph sources can point to exact anchors.
- Separate requirements, decisions, considered options, concise rationale, acceptance evidence, and outcomes. Do not present a plan as delivered fact.
- 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 Decisionfor an accepted choice;## Rejected Alternativeor## Declined Optionfor an option not taken;## Superseded Decisionwhen 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.
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.
- 7d ago First seen · 94 lines · 46 tokens per session scan A 3fe1e8c4c147
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.
Other skills, from other repositories
lever-new
Start a new lever — discuss the ask in chat, then capture intent (Goal, Success sketch, Context, Open questions) as §Brief. Hands off via /lever .
lever-status
Inspect or cancel levers. List all (no arg), detail one (TL;DR + criteria + per-criterion events timeline), or cancel one with cancel [ ]. Never advances the chain.
lever-init
Bootstrap a repo for agent-levers. Creates .agents/levers/, wires CLAUDE.md/GEMINI.md to import AGENTS.md, writes an AGENTS.md skeleton when missing. Hands off via /lever-new.
run-agent-evolution
Run phase of an agent evolution — plan a batch of up to budget.parallel variants, dispatch sub-agents in parallel to materialize and evaluate them, learn from results, repeat until budget / wall-clock / plateau. Writes winner on a clean stop. Requires an evolution captured via /new-agent-evolution…
lever
Advance an existing lever. Reads lever.yaml.step and runs the chain (plan → do → check → act → done) autonomously until it pauses or finishes.
new-agent-evolution
Capture phase of an agent evolution — discuss the objective, gates, rubric, scope, and budget; write .agents/evolutions/ - /{evolution.yaml, EVOLUTION.md} only on explicit user agreement. Pairs with /run-agent-evolution (next) and /apply-agent-evolution (later).