execute-use-case

execute-use-case is a skill for Claude Code, Codex from jeunessegamesee/clew. It costs 46 tokens per session (392 once invoked), scanned A, original, MIT.

A method for following one already documented service flow through its matching conditions and outputs. It uses a use-case tree, where a use case is one concrete job the system performs, instead of exploring the whole system.

In plain words
What is it for?
Use it to implement or debug a known request, event, webhook, or asynchronous flow, follow calls into another service when needed, and update the map after finding a missing path.
Why use it?
It makes implementation and debugging focused by loading only the relevant path and exposes missing branches or broken links when the path cannot be followed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/jeunessegamesee/clew/execute-use-case
Any agent
npx skills add jeunessegamesee/clew --skill execute-use-case
Clone the repo
git clone --depth 1 https://github.com/jeunessegamesee/clew

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.

agentmods badge for execute-use-case

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeunessegamesee/clew/execute-use-case.svg)](https://agentmods.dev/skills/jeunessegamesee/clew/execute-use-case)
Your own site
<a href="https://agentmods.dev/skills/jeunessegamesee/clew/execute-use-case"><img src="https://agentmods.dev/badge/skills/jeunessegamesee/clew/execute-use-case.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 392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00392
Opus 5 $0.00023 $0.00196
Sonnet 5 $0.00009 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured 4d ago against content hash 6b75d680b10b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

execute-use-case 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.

skills/execute-use-case/SKILL.md · 22 lines

What it actually says

Execute a use case

You are in execute mode. The team already paid to map this flow.

The map is a tree. Walk one path. Do not treat every node as HTTP.

  1. Run clew loadout --root <repo> --use-case <tree> --payload '<json>' (or MCP loadout). That is the only path you load. If hops.md is missing, stop and ask to cartograph.
  2. Pick the tree: match inbound event/request to the forest (dispatch) if you do not already have a tree id.
  3. Descend only matching when branches (plus matching also). when supports == != && || and dotted fields.
  4. Output nodes: follow that node’s interaction (trace vs stitch key vs new webhook trace).
  5. next is another tree in another repo — open it only when you work that hop.
  6. Fall off the tree (else) or hit a dangling next: that is red. Capture the smallest proven node, then clew loop --root <repo>. Do not guess a whole tree. If this is a monorepo, add the edge to root docs/flows.md.
  7. Do not invent or unify DTOs across paths or services.
  8. After a trap or a proven path: write it on this tree. The map should be better at the end of the session.

If hops.md calls the interaction “async” only, classify it (command vs event vs request-reply) while you work and fix the file in the same change.

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. 4d ago First seen · 22 lines · 0 tokens per session scan A 6b75d680b10b

Subscribe to this mod's changes

execute-use-case is a skill published in the GitHub repository jeunessegamesee/clew (0 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 392 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.