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.
git clone --depth 1 https://github.com/btspoony/mstar-harnessWrote 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/commands/btspoony/mstar-harness/iteration-loop)<a href="https://agentmods.dev/commands/btspoony/mstar-harness/iteration-loop"><img src="https://agentmods.dev/badge/commands/btspoony/mstar-harness/iteration-loop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/btspoony/mstar-harness/iteration-loop"><img src="https://agentmods.dev/badge/commands/btspoony/mstar-harness/iteration-loop.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00065 | $0.00658 |
| Opus 5.5 | $0.00026 | $0.00263 |
| Sonnet 5.5 | $0.00013 | $0.00132 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
iteration-loop 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iteration Loop
The whole lifecycle with an autonomous direction lock: this command's explicit autonomous opt-in replaces the interactive direction dialogue. Sibling entries: /iteration-start locks interactively and /iteration-drive resumes a locked iteration. Done = Phase 6 post-merge close.
Args
/iteration-loop [direction] [scale] — a trailing token exactly S / M / L / XL (case-insensitive) is scale, default M; the remaining text is direction (a lone scale token means an empty direction). Scale budgets the iteration's business plans only (S 1 / M 2–3 / L 3–4 / XL >4) — budget rules and what stays outside it → mstar-iteration/references/autonomous-direction-lock.md § Scale budget.
Boot
mstar-harness-core → mstar-roles → references/project-manager.md → mstar-iteration (route map: start → references/phase-1-prepare.md) → mstar-iteration/references/command-shared-invariants.md.
Execute
- Phase 1 — autonomous start → execute
mstar-iteration/references/phase-1-prepare.md§1.1–§1.6 withDirection lock mode: autonomous(ranking, branch resolve, prototype disposition →references/autonomous-direction-lock.md). Retain a prototype (HTML, Markdown or JSON) with format rationale and autonomous disposition; never fabricate user approval. Do not readskills/grill-me/SKILL.mdfor this entry. Host Plan-mode permissions still apply — use the active host bridge's supported resume. Print the §1.6 Phase 1 completion checklist: clear the pre-integration items before the §2.3 integration step and mark the integration item after the branch push; loop session todophase-1-autonomous-startcloses when the compass is locked and the integration branch is pushed. - No credible candidate and no
direction→ STOP and escalate; never invent a direction or default the branch policy. - Phase 2→6 → continue through
iteration-driveexactly (same route map, gates, phase headers and report). Continuous execution and STOP rules →mstar-iteration§2.6 pluscommand-shared-invariants.md.
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 Changed · -74 lines · -32 tokens per session a8aa4cf4f05f
- 13d ago Changed fd83e3f949e4
- 17d ago Changed 053e0d7c675c
- 19d ago Changed · +3 lines · +6 tokens per session d853e9f830c3
- 25d ago Changed 9fb40a323303
- 1mo ago Changed · +1 lines 2df62b9a6cd1
- 1mo ago Changed · +8 tokens per session 17dde25c9bda
- 1mo ago Changed 452c5607c034
- 1mo ago First seen · 100 lines · 83 tokens per session scan A 6b580c6f53c1
iteration-loop is a command published in the GitHub repository btspoony/mstar-harness (64 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 658 once invoked, about $0.0003 per session on Opus 5.5. 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 commands, from other repositories
add-changelog
Generate and maintain project changelog.
create-release-note
Generate comprehensive release documentation from recent commits, producing two distinct outputs: a customer-facing release note and a technical engineering note.
opensource
Prepare a project or module for open-source release. 3-phase pipeline - strip secrets, sanitize, package with docs.
ship-readiness
Review whether a candidate or workflow is truly ready to ship.
land
Resolve and squash merge one named, currently authorized pull request.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.