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 commands/proggarapsody/bitbottle/auto-iter-streamgit 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 | $0.00043 | $0.00762 |
| Opus 5 | $0.00022 | $0.00381 |
| Sonnet 5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
auto-iter-stream 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/auto-iter-stream — Claude Code adapter
Chain-loop mechanic: run N /auto-iter cycles back-to-back with no inter-cycle wait.
Lock/halt/cadence/metrics: see .claude/commands/auto-iter.md.
Full procedure: docs/workflows/iteration-cycle/README.md.
Argument parsing
max = $1 (first arg). Validation:
- Missing or empty → error, exit immediately. Do not default.
- Not a positive integer → error, exit.
> 10→ error, exit. (Hard ceiling; raise manually if genuinely needed.)
Announce: stream started — max=<N>, ran=0.
Pre-flight
LOCK=.claude/auto-iter/.lock
if [ -f "$LOCK" ]; then
LOCK_AGE_MIN=$(( ($(date +%s) - $(stat -f %m "$LOCK" 2>/dev/null || stat -c %Y "$LOCK")) / 60 ))
[ "$LOCK_AGE_MIN" -lt 60 ] && exit # abort — another cycle is running
fi
Log stream start: {"ts":"<ISO>","stream":"started","max":<N>,"ran":0}
Loop logic
ran = 0
while ran < max:
execute one full /auto-iter cycle (per .claude/commands/auto-iter.md)
cycle_outcome = <last line in cycles.jsonl written by this cycle>
if cycle_outcome starts with "halt_" OR cycle_outcome == "skip_in_progress":
final_outcome = "stream_halted"; break
if cycle_outcome == "shutdown_confirmed":
final_outcome = "stream_shutdown"; break
ran += 1
if ran == max: final_outcome = "stream_max_reached"
append: {"ts":"<ISO>","stream":"completed","stream_started":"<ISO>","max":<N>,"ran":<ran>,"final_outcome":"<final_outcome>"}
stream_* outcomes
| Value | Meaning |
|---|---|
stream_max_reached |
ran = max, all cycles shipped |
stream_halted |
a halt_* stopped the chain |
stream_shutdown |
BACKLOG empty + 3 empty brainstorms |
stream_aborted_lock_held |
pre-flight found a fresh lock |
Halt routing
Mid-cycle halts (halt_release, CI red, pre-merge BLOCKER) are handled inside each
/auto-iter cycle. ship reply → cycle ships, stream continues. hold reply →
halt_release outcome → stream stops.
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.
- 3d ago First seen · 77 lines · 43 tokens per session scan A e95de38fd000
auto-iter-stream is a command published in the GitHub repository proggarapsody/bitbottle (3 stars, last pushed 15d ago), licensed MIT. It adds 43 tokens to every session and 762 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 2026-08-31.
Other commands, from other repositories
test-e2e
Write end-to-end tests for critical user journeys.
test-integration
Write integration tests for component boundaries.
export
Design public API exports.
newpkg
Generate new package with Nx.
init
Initialize goal-flight state for a project.
doctor
Run procedural readiness checks for goal-flight.