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.
npx agentmods add instructions/gtrabanco/agentic-workflow/claude-mdgit clone --depth 1 https://github.com/gtrabanco/agentic-workflowWrote 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/instructions/gtrabanco/agentic-workflow/claude-md)<a href="https://agentmods.dev/instructions/gtrabanco/agentic-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/gtrabanco/agentic-workflow/claude-md.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 | $0.04297 | $0.04297 |
| Opus 5 | $0.02148 | $0.02148 |
| Sonnet 5 | $0.00859 | $0.00859 |
| Haiku 4.5 | $0.00430 | $0.00430 |
Grade A, and why
agentic-workflow CLAUDE.md 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 4d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for AI coding agents working in this repository (agentic-workflow).
This repo is not an application. It ships two things:
skills/— a stack-agnostic set of agent skills that run a disciplined, doc-driven feature/issue workflow. Each is oneskills/<name>/SKILL.md.template/— an exportable documentation scaffold: the way of working (documentation map, SPEC/feature/fix templates, GitHub templates, conventions) that a target project copies so the skills have a substrate to operate on.
The skills are project-adaptive: at runtime they discover and obey the target project's own guide, documentation map, architecture, roadmap and style docs. Nothing here is tied to a specific stack, framework, or architecture pattern.
Repository layout
skills/ the workflow skills (one SKILL.md each) — the installable source
.claude/skills symlink → ../skills, so this repo dogfoods them in Claude Code
template/ the exportable documentation scaffold (generic, copyable)
packages/ two companion npm packages (bun-managed islands — see Packages below)
docs/workflow/ the tutorial: feature flow, issue flow, skill reference, replication
docs/features/_TEMPLATE feature SPEC template + ROADMAP
docs/fix/ fix SPEC template + index
.github/ issue + PR templates the workflow expects
README.md / README.es.md project overview (EN / ES)
Working rules
- Docs language is English. Every committed artifact (skills, docs, templates, commits, PR descriptions) is in English, regardless of the language used to request the work. Reply to the user in the user's language.
- Human-readable docs carry EN + ES siblings.
README,CHANGELOG,docs/workflow/*.md, and the schema packageREADMEeach get a faithful.es.mdsibling with reciprocal language-switcher links (> 🇪🇸 [Versión en español](<name>.es.md)on the English original,> 🇬🇧 [English version](<name>.md)on the Spanish sibling). Hard rule — the ES sibling is updated in the SAME change, never deferred. If a change edits an English doc that has a.es.mdsibling (or is documentation that should be translated), it MUST update the Spanish version in the same commit/PR — a diff that touches only the English side of a bilingual pair is incomplete and must not be committed or merged. This is not "on next touch, best effort": whoever edits the English doc owns the reciprocal ES edit right then. There is no automated staleness check, so the rule is enforced by the author and by review. Scope exception:SKILL.md, SPECs, commits, PRs, and machine config (model-routing.yml) stay English-only per the docs-language rule above and have no ES sibling — the bilingual sync rule applies only to docs that actually have a translatable sibling (human tutorial/reference prose), never to process artifacts. - Stack/architecture agnostic. Do not introduce references to any specific product, stack, framework, ORM, runtime, or architecture pattern into the skills or the shared docs. Generic phrasing ("the project's architecture", "the project's verification gate") is the rule.
- One PR per unit of work, always against
main. Never work onmaindirectly; never stack PRs (a PR's base is alwaysmain). - Commit format: conventional commits, e.g.
feat(skills): add execute-phase,docs(workflow): clarify replicate steps,chore(template): add brand stub.
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.
- 4d ago First seen · 313 lines · 4,297 tokens per session scan A 3d4443c56438
agentic-workflow CLAUDE.md is an instructions file published in the GitHub repository gtrabanco/agentic-workflow (20 stars, last pushed 4d ago), licensed MIT. It adds 4,297 tokens to every session, about $0.0215 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 2026-08-30.
Other instructions, from other repositories
claude-code-toolkit CLAUDE.md
Claude Code instructions for robertguss/claude-code-toolkit, covering claude.md, project overview, build commands, package a single skill for claude.ai upload and package all skills.
fw-dev-tools AGENTS.md
Instructions for freshworks-developers/fw-dev-tools, covering agent instructions — marketplace repo (contributors), before you open a pr, if you change…, repository layout and rules and slash commands (inventory).
fw-dev-tools CLAUDE.md
Instructions for freshworks-developers/fw-dev-tools: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.