What is ferrus-executor?

A playbook for making focused code changes and submitting them in Ferrus, a development workflow that provides its own tools and checks.

Use it to navigate code from public entry points, make small fixes, run Ferrus checks, apply test-driven development when suitable, and document verification steps.

It helps avoid unrelated edits and catches hidden dependencies, test assumptions, and side effects before submission.

How ferrus-dev/ferrus configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to ferrus-dev/ferrus. 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/ferrus-dev/ferrus/main/.agents/skills/ferrus-executor/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ferrus-dev/ferrus

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ferrus-dev/ferrus/ferrus-executor/github.svg)](https://agentmods.dev/skills/ferrus-dev/ferrus/ferrus-executor)

Your own site

<a href="https://agentmods.dev/skills/ferrus-dev/ferrus/ferrus-executor"><img src="https://agentmods.dev/badge/skills/ferrus-dev/ferrus/ferrus-executor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ferrus-dev/ferrus/ferrus-executor"><img src="https://agentmods.dev/badge/skills/ferrus-dev/ferrus/ferrus-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 435 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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.00435
Opus 5.5	$0.00008	$0.00174
Sonnet 5.5	$0.00004	$0.00087
Haiku 4.5	$0.00002	$0.00044

Measured 12d ago against content hash df919d138c5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ferrus-executor 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 12d 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/ferrus-executor/SKILL.md · 65 lines

What it actually says

Executor Operating Playbook

This file is advisory only. Runtime workflow is defined by the initial prompt and exposed Ferrus tools.

Implementation guidelines

Prefer minimal, targeted diffs
Avoid unrelated refactoring
Preserve existing project patterns unless the task requires otherwise

Start from entrypoints and public interfaces
Trace dependencies before changing behavior
Inspect surrounding code before modifying shared logic

Common pitfalls

Hidden side effects
Implicit contracts between modules
Test coupling and fixture assumptions
State transitions that depend on tool behavior

Ferrus guidance

Use the host-selected session mode and exposed tools rather than reconstructing state from .ferrus/
In managed MCP sessions, use wait/heartbeat tools; Nano hosts own those operations
Direct HQ and standalone sessions have no managed task to claim or submit; validate with their exposed tools
Use exposed validation tools during development; managed work uses check for durable receipts
For managed work, run check immediately before submit; final response text is not submission
Read Ferrus resources when exposed; Nano uses native context and load_instructions
Ferrus owns managed Git staging and integration; direct sessions change Git state only when the user requests it
For managed consultation, use the exposed consultation context/template when available

Submission quality

Provide a clear summary of what changed
Include concrete manual verification steps
Mention limitations or follow-up work explicitly when relevant

Useful Ferrus tools

/wait_for_task
/heartbeat (while owning the task lease)
/check
/consult
/wait_for_consult
/ask_human
/wait_for_answer
/submit

Useful Ferrus resources

ferrus://task
ferrus://review
ferrus://consult_template
ferrus://question
ferrus://answer

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

ROLE.md 816 B

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.

12d ago Changed · +3 lines df919d138c5a
2mo ago Changed · +1 lines 35d36d31f0c6
2mo ago First seen · 61 lines · 21 tokens per session scan A f409b8c7f2d8

Subscribe to this mod's changes

ferrus-executor is a skill published in the GitHub repository ferrus-dev/ferrus (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 21 tokens to every session and 435 once invoked, about $0.0001 per session on Opus 5.5. 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.

agent-orchestration ai-agents automation deterministic-systems developer-tools mcp

ferrus-executor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ferrus-executorferrus-dev/ferrus	Skill	2	7d ago	Apache-2.0	A	21	Claude Code, Codex
paperclippaperclipai/paperclip	Skill	111k	yesterday	MIT	A	54	Claude Code, Codex
index-refreshpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	43	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	111k	yesterday	MIT	A	30	Claude Code, Codex
ppt-reviewOrkas-AI/Orkas	Skill	9.0k	yesterday	MIT	A	2	Claude Code, Codex
cw-gatesHmbown/Codewhale	Skill	41k	1mo ago	MIT	A	48	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	33	Claude Code, Codex

ferrus: Skill for Claude Code