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 skills/brain-bootstrap/claude-code-brain-bootstrap/codeburnnpx skills add brain-bootstrap/claude-code-brain-bootstrap --skill codeburngit clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrapWhat 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 | $0.00032 | $0.00514 |
| Opus 5 | $0.00016 | $0.00257 |
| Sonnet 5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
codeburn 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 2d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codeburn — Token Cost Observability
Reads directly from ~/.claude/projects/ (no API keys, no wrappers) and renders a TUI dashboard showing where tokens go.
Complementary to rtk: rtk reduces tokens spent (efficiency); codeburn shows which tasks need optimization most (observability). Together they close the feedback loop.
Key Commands
codeburn # Interactive TUI dashboard (keyboard navigation)
codeburn today # Today's sessions only
codeburn report -p 30days # 30-day rolling window
codeburn report --project <name> # Filter by project
codeburn export --format csv # Export for further analysis
codeburn export --format json # JSON output
What It Measures
| Metric | Why it matters |
|---|---|
| Tokens by task type (13 categories) | Find which work type is most expensive |
| One-shot rate per task type | % tasks done in 1 API call vs retry loop |
| Per-model breakdown | Cost difference between Opus and Sonnet for your actual tasks |
| USD cost estimate | Real spend per session / project |
| Input vs output token split | Output tokens cost 3-5× more than input |
The 13 Task Categories
refactor · bug-fix · feature · test · docs · review · debug · config · migration · research · security · cleanup · other
Optimization Feedback Loop
codeburn report → find low one-shot rate task type
→ add context/rules for that category in CLAUDE.md or claude/*.md
→ rtk reduces token output on those commands
→ re-run codeburn to verify improvement
Signal: If one-shot rate < 50% for a task type, it needs more upfront context or better rules.
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.
- 2d ago First seen · 58 lines · 32 tokens per session scan A 08367fe91dbc
codeburn is a skill published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 514 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 2026-08-30.
Other skills, from other repositories
implement
TRIGGER when: user asks to implement, fix, build, or work on something — whether from a docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Examples: "work on task 1", "fix this bug", "implement feature X from the issue". Provides structured execution with profile detection, dependency…
review-spec
Use after implementing tasks or mid-feature to verify code matches design docs and ensure they are in sync. Detects spec deviations, missing implementations, doc inconsistencies, and outdated docs in design and implementation documentation.
chain-of-verification
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.
review-design
Review design, implementation, and task documents produced by design. Evaluates document quality, internal consistency, and technical soundness. Use after design completes and before starting implement.
review-code
Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.
dependency-handling
TRIGGER when: adding or upgrading any dependency — library, SDK, framework, API, IaC API version (K8s/Terraform/Helm), CRD, or container image. Use BEFORE writing the call. Forces context7/capy lookup instead of guessing.