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/chevp/chevp-workflow/claude-mdgit clone --depth 1 https://github.com/chevp/chevp-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/chevp/chevp-workflow/claude-md)<a href="https://agentmods.dev/instructions/chevp/chevp-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/chevp/chevp-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 | $0.01219 | $0.01219 |
| Opus 5 | $0.00609 | $0.00609 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
chevp-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 3d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — chevp-workflow
This is a workspace-level process framework for AI-assisted development across multiple repositories. It defines the meta-lifecycle that Claude must follow whenever an action touches more than one repo.
Core Principle
The human writes naturally. The AI detects whether a request is single-repo or workspace-scope.
Workspace mode is opt-in by intent: reads stay trivial, writes across repos require the full workspace lifecycle. The human never declares "workspace mode" — the AI infers it from the intended blast radius.
This framework is orchestration-driven: single-repo work is delegated to chevp-ai-framework. chevp-workflow owns only what lives between repos (impact, sequencing, orchestration).
Core Rules
- Trivial reads stay trivial — Never load this framework for read-only intent
- Any cross-repo write enters workspace mode — Even one commit across two repos counts
- One primary owner per plan — Every workspace plan lives in exactly one repo; others get reference stubs
- Delegation is mandatory — Per-repo work is handed down to
chevp-ai-framework, not duplicated here - Gates are blockers — G0 through G3 must be satisfied before forward movement
- Secondary repos never own scope — Only the primary owner's plan can drive scope changes
- Cross-platform by default — All paths, commands, and examples must work on Windows, macOS, and Linux (see guidelines/cross-platform.md)
- No AI attribution in commits — Never add Claude/AI co-authorship or tooling references to commit messages or PR bodies (see guidelines/no-ai-attribution.md)
Lifecycle: 3 Steps × 6 Roles × 4 Gates
1. Discover → 2. Coordinate → 3. Execute
The AI infers workspace mode from intent. Before every write-action response the AI:
- Detects whether the action affects >1 repo (git root)
- Enters workspace mode if yes; stays in per-repo mode if no
- Announces the workspace step it is currently in
- Checks gate prerequisites — blocks if unmet, explains what is missing
- Acts within the boundaries of the current workspace step
- Delegates per-repo execution to
chevp-ai-frameworkonce the workspace plan is approved
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.
- 3d ago First seen · 83 lines · 1,219 tokens per session scan A 40963096df3b
chevp-workflow CLAUDE.md is an instructions file published in the GitHub repository chevp/chevp-workflow (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,219 tokens to every session, about $0.0061 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 instructions, from other repositories
ESAA-Core AGENTS.md
Instructions for elzobrito/ESAA-Core, covering agents.md — contrato operacional codex/esaa, 1. autoridade e termos, 2. cli e runner, ou configure o runner uma vez por sessão and 3. concorrência.
Kanvas AGENTS.md
Instructions for XMihura/Kanvas, covering canvas workflow — agent instructions, critical rule, session protocol, 1. start of session — read the board and 2. pick a task.
delivery-loop CLAUDE.md
Instructions for blakemartz/delivery-loop, covering claude.md, what this is, the cardinal rule: everything must stay repo-agnostic, layout and config: the one seam.
taskcenter AGENTS.md
AGENTS.md instructions for xiaogezi/taskcenter, covering taskcenter agent rules, safety boundaries, required workflow and verification.
idd-skill idd-resume.instructions.md
Instructions for kurone-kito/idd-skill, covering idd — resume phase, required inputs, step 0 — route classifier, operator-present release and step 1 — identify claim state.
kanban-lite AGENTS.md
AGENTS.md instructions for borgius/kanban-lite, covering kanban markdown - development guide, repo-wide defaults and post-change verification (mandatory).