Metrics
Cost-focused project metrics, broken down per component — LOC by language and component, duplicate-function groups, directive health, always-on context cost (CLAUDE.md tokens × turns), local-routing posture, skill-search tokens avoided, and the audit's own (near-zero) cost. Use when the user wants to quantify a project's token/cost profile, see LOC/health per component, or measure what the toolki…
Install
$ agentstack add skill-zedarvates-botte-secrete-metrics ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-zedarvates-botte-secrete-metrics) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
metrics — quantify a project's token/cost profile
Surfaces the numbers an audit should give you, framed around cost. A multi-stack project (website + game server + client + tools) has no single number, so everything is broken down per component.
python -m skills.metrics.cli
python -m skills.metrics.cli --porthos reports//audit-report.json --jsonWhat it reports
- LOC by language and by top-level component (with bars).
- Duplicate-function groups (stdlib AST, free).
- Directive health + always-on context cost: instruction tokens × turns
— e.g. a 2.3k-token CLAUDE.md ≈ 70k tokens/session just re-sending rules.
- Local-routing posture: backends present → cheap work at 0 cloud tokens.
- Skill-search tokens avoided by
find_skills(catalog × ~150 tok). - The audit's own cost:
analysis_llm_tokens = 0— the scans are
deterministic Python; only synthesis by the orchestrating model costs tokens.
- Deep audit summary (health / dead code / secrets) if a Porthos
audit-report.json is reachable (.botte/ or --porthos).
Why this framing
The headline an audit should produce: "analysis cost 0 tokens; your always-on instructions cost ~70k/session; local routing can move cheap work to 0 cloud tokens." That's the number that justifies the toolkit.
Exposed via [[llmmcp]] as the metrics tool. Related: [[infraadvisor]] (auto audit), [[directivesaudit]], [[skillfinder]], [[bootstrap]].
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: zedarvates
- Source: zedarvates/botte-secrete
- License: MIT
- Homepage: https://github.com/zedarvates/botte-secrete
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.