Index of every page on this site: llms.txt
All skills
ccusage avatar

/agent-sources

@7e789e8
by ccusageccusage/ccusage20k stars
934
Run it yourself

Guides ccusage agent source formats. Use when checking where an agent stores its logs, how raw records map to tokens and models, how precomputed costs interact with cost modes, or which reports an agent supports.

Use this Skill: https://skilld.dev/gh/ccusage/ccusage/agent-sources

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈57 tokens for metadata: the name and description. ≈161 when used: this file.

Description uses 2.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈228 characters, or 2.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

ccusage Agent Sources

Read rust/adapters/<agent>/README.md and, where present, src/README.md for source paths, record shapes, and accounting rules. Follow the adapter and pricing candidate boundaries in rust/adapters/README.md and the change workflow in rust/adapters/AGENTS.md.

Keep command and option semantics aligned across agents. Declare supported reports in rust/crates/ccusage-cli/src/agents.rs. Preserve source-specific stored-cost, reasoning-token, and residual-token policies. Follow the cost-mode contract in docs/guide/cost-modes.md and reuse rust/crates/ccusage-core/src/cost.rs when it preserves those policies.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    No security issues detected. The skill provides technical documentation and architectural guidance for using the ccusage CLI tool and its associated agent adapters.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at 7e789e8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated yesterday

README badge

README badge for ccusage/ccusage/agent-sources