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 agents/proggarapsody/bitbottle/01-metricsgit clone --depth 1 https://github.com/proggarapsody/bitbottleWrote 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/agents/proggarapsody/bitbottle/01-metrics)<a href="https://agentmods.dev/agents/proggarapsody/bitbottle/01-metrics"><img src="https://agentmods.dev/badge/agents/proggarapsody/bitbottle/01-metrics.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 | $0.00000 | $0.03769 |
| Opus 5 | $0.00000 | $0.01885 |
| Sonnet 5 | $0.00000 | $0.00754 |
| Haiku 4.5 | $0.00000 | $0.00377 |
Grade A, and why
01-metrics 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.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metrics Agent Report — cycles 153–187 (2026-06-02)
Analysis dimension: METRICS — quality, completeness, and trustworthiness of auto-iter instrumentation; what the metrics reveal about cycle performance.
TL;DR
- Data completeness is 37% overall (11/30 cycles have all five key fields populated); the dominant gap is the 168–177 zero-emission regime where tokens, duration, and metric steps were never written.
- TDD dominates wall time at 84–92% of instrumented step time (cycles 178–187 median 9.6 min/cycle); design-judge consumes a consistent 8–17%; CI wait and PRD are not instrumented in the latest stream at all.
- Design judge ran in 12/30 cycles and flagged blockers in 7 of the 11 cycles
where
blocker_countwas recorded (64% blocker rate); all 7 were confirmed real (0% false-positive rate per stream-178-187 report). - Five distinct instrumentation defects exist: corrupt
duration_wall_minon cycle 157 (29.6M min instead of 31 min); field-name inconsistency (blockersvsblocker_count); step-name drift across 4 canonical groups;metrics_steps_countmismatches on 4 cycles; and five cycles (162, 163, 165, 166, 167) entirely absent from both dataset and rawcycles.jsonl.
1. Data Completeness
Five key fields assessed: tokens > 0, duration_active_min > 0, release
populated, scopes populated, _metric_steps non-empty. Brainstorm cycles
excused from release requirement.
| Regime | Cycles | tokens>0 | duration>0 | scopes | steps>0 | DJ step | Fully complete |
|---|---|---|---|---|---|---|---|
| 153–164 (pre-stream) | 10 | 6/10 | 9/10 | 7/10 | 8/10 | 4 | 1/10 (10%) |
| 168–177 (zero-logged) | 10 | 0/10 | 0/10 | 10/10 | 1/10 | 0 | 0/10 (0%) |
| 178–187 (instrumented) | 10 | 9/10 | 9/10 | 10/10 | 10/10 | 8 | 10/10 (100%) |
| Total | 30 | 15/30 | 18/30 | 27/30 | 19/30 | 12 | 11/30 (37%) |
Five cycles completely absent (162, 163, 165, 166, 167) from both the
dataset and cycles.jsonl — they have entries in metrics.jsonl only. This
leaves a 5-cycle gap in any per-cycle lineage analysis. The metrics.jsonl entries
for 162 and 163 show only step3_tdd + step8_ship (no CI wait, no DJ). Cycle
165 has a corrupt step2_prd duration (see §5).
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.
- 4d ago First seen · 244 lines · 0 tokens per session scan A 7544bb425125
01-metrics is an agent published in the GitHub repository proggarapsody/bitbottle (3 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,769 tokens. 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 agents, from other repositories
release-bundle-testing
Rozenite is a development tool. Whatever a project wires into its bundler config, a release build must ship none of our code. @rozenite/test-utils provides the bench that proves it, and every plugin owns a Vitest suite in src/tests/release-bundle.test.ts that uses it.
e2e-testing
pnpm expo run:ios pnpm expo run:android.
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
playground-testing
Rozenite DevTools plugins. Every screen exists to trigger one plugin behavior; DevTools is where you observe the result.
debugger
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
domain
This document defines the canonical domain language for Vibelution so architecture work can use stable names for the same concepts. It is intentionally small: add terms when they become load-bearing in design or tests.