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/02-reportsgit clone --depth 1 https://github.com/proggarapsody/bitbottleWhat 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 | $0.04065 |
| Opus 5 | $0.00000 | $0.02032 |
| Sonnet 5 | $0.00000 | $0.00813 |
| Haiku 4.5 | $0.00000 | $0.00407 |
Grade A, and why
02-reports 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report dimension audit — cycles 158–187 (2026-06-02)
Dimension: REPORTS — quality, accuracy, and usefulness of post-stream analysis reports.
Audited reports: stream-2026-05-24-cycles-135-144.md, stream-2026-05-25-cycles-145-154.md,
stream-2026-05-29-cycles-168-177.md, stream-2026-06-01-cycles-178-187.md.
Ground truth: analysis-2026-06-02-cycles-158-187/dataset.json and .claude/auto-iter/cycles.jsonl.
TL;DR
Four stream reports cover cycles 135–187, with a hard 13-cycle documentation gap at 155–167 that has no report and 5 cycles (162, 163, 165, 166, 167) missing from the underlying data entirely. Naming convention compliance is 100%. Section compliance improved sharply across the four reports (0/6 required sections in the earliest two vs 6/6 in 168–177), but the most recent report (178–187) regresses on two sections. The 178–187 report contains four factual errors traceable to ground-truth data: the follow-up-fix count is 5 but should be 6; the token-emission rate is 8/10 but should be 9/10 (or 10/10 counting metric-step tokens); the median token figure is 180K but the correct value is 188.1K; cycle 181 is described as "clean" but had a DJ BLOCKER caught pre-merge. Recommendations across all reports are well-ranked and actionable but lack a closed-loop section: no report explicitly confirms which prior fixes were applied before the stream it describes.
Coverage map
| Cycle range | Report file | Status |
|---|---|---|
| 135–144 | stream-2026-05-24-cycles-135-144.md |
Documented |
| 145–154 | stream-2026-05-25-cycles-145-154.md |
Documented (cycles 153–154 are the tail) |
| 155–167 | (none) | UNDOCUMENTED GAP — 13 cycles |
| 168–177 | stream-2026-05-29-cycles-168-177.md |
Documented |
| 178–187 | stream-2026-06-01-cycles-178-187.md |
Documented |
Gap detail: cycles 155–167
Thirteen consecutive cycles (2026-05-25 → 2026-05-29) have no stream report. Of these:
| Cycle | Scope (from dataset.json / cycles.jsonl) | Data present? |
|---|---|---|
| 155 | brainstorm (+10 scopes) | Yes |
| 156 | PIPE-CONFIG+SSH-KEY-SERVER | Yes |
| 157 | PIPE-TEST-REPORTS+BRANCH-COMPARE | Yes |
| 158 | REPO-DOWNLOAD+MILESTONES | Yes |
| 159 | ISSUE-VERSIONS+WORKSPACE-PROJECT-CRUD | Yes |
| 160 | REPO-MIRROR+WORKSPACE-PERMS | Yes |
| 161 | brainstorm (+8 scopes) | Yes |
| 162 | unknown | No — missing from dataset.json and cycles.jsonl |
| 163 | unknown | No — missing from dataset.json and cycles.jsonl |
| 164 | REPO-CLONE | Yes |
| 165 | unknown | No — missing from dataset.json and cycles.jsonl |
| 166 | unknown | No — missing from dataset.json and cycles.jsonl |
| 167 | unknown | No — missing from dataset.json and cycles.jsonl |
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 · 238 lines · 0 tokens per session scan A eb71ae4af29f
02-reports is an agent published in the GitHub repository proggarapsody/bitbottle (3 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,065 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
validation
How to run checks in this repository without rebuilding all 38 packages for a two-file change.
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.
plugin-development
src/tests/release-bundle.test.ts proving its DevTools panel cannot reach a shipped app; plugins exporting a bundler integration (./metro) guard that too. See release bundle testing.
debugger
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.