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-drive)<a href="https://agentmods.dev/commands/btspoony/mstar-harness/iteration-drive"><img src="https://agentmods.dev/badge/commands/btspoony/mstar-harness/iteration-drive/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-drive"><img src="https://agentmods.dev/badge/commands/btspoony/mstar-harness/iteration-drive.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 | $0.00038 | $0.00612 |
| Opus 5.5 | $0.00015 | $0.00245 |
| Sonnet 5.5 | $0.00008 | $0.00122 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
iteration-drive 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive Iteration
Drive the selected iteration to completion with one primary coordinator. Not Done until Phase 6 post-merge close — a Phase 3 close, an open PR or a merge-ready exit is not delivery.
Entry
Accepts no arguments: reject a nonempty invocation before boot and name the supported no-argument form instead of broadening its scope. A leaf executor that receives this command refuses it on role grounds (mstar-dispatch-gates) and never promotes itself to PM.
Boot
mstar-harness-core → mstar-roles → references/project-manager.md → mstar-iteration → mstar-iteration/references/command-shared-invariants.md (Phase 2–5 PM invariants, assignment preflight, session todos, continuous-execution STOP list) → the current phase's detail reference only.
Execute
Phase route and transition gates → mstar-iteration ## Phase route map / ## Phase transition gates: run Phase 2 → 3 → 4 → 5 → 6 in order, loading only the current phase's detail and printing each ## Phase N header at its boundary. Phase 5 optional helper-skill discovery → mstar-iteration/references/phase5-helper-discovery.md (non-mstar-* helpers stay out of the mstar-* load order). Continuous execution → mstar-iteration §2.6.
Merge is authorized by the compass pr_merge_policy, never by flow completeness: under reviewed-auto Phase 5 runs the PR-level review loop and only a settled, posted ship it report whose head equals the current PR head authorizes the merge; under owner-gated Phase 5 stops at merge-ready and waits for the human owner's (the operator, not this harness's coordinator seat) explicit written approval of the current PR head. A missing pr_merge_policy is a STOP back to Phase 1 — never infer a default. Rules and every refusal recovery → mstar-iteration → references/phase-4-5-pr-delivery.md §5.3. A verified merge immediately enters Phase 6.
Report
Iteration id, plans completed, compound summary, PR link, merge-ready evidence, the recorded pr_merge_policy and the merge-authorization evidence that satisfied mstar-iteration → references/phase-4-5-pr-delivery.md §5.3, and post-merge close evidence (workflow completed + ended_at, root unregister, projections consistent).
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 ceb89e5f5547
- 4d ago Changed · -32 lines · -48 tokens per session f4ecf34e86e6
- 18d ago Changed · -10 lines 49129c4ea47c
- 19d ago Changed 3d52c814f0ef
- 25d ago Changed · +2 lines 8482be421c46
- 26d ago Changed 4f81207649f5
- 1mo ago Changed 8cb9638a45d7
- 1mo ago Changed · +14 lines d4b075219f68
- 1mo ago Changed · +6 lines · +14 tokens per session d8141feb23e1
- 1mo ago First seen · 49 lines · 72 tokens per session scan A 9fe9cadad4a0
iteration-drive is a command published in the GitHub repository btspoony/mstar-harness (64 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 612 once invoked, about $0.0002 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
create-release-note
Generate comprehensive release documentation from recent commits, producing two distinct outputs: a customer-facing release note and a technical engineering note.
release
Prepare and publish spec-driven-steroids through the tag-triggered npm release pipeline.
lavra-ship
Fully automated ship sequence from code-ready to PR-open with beads closed and knowledge captured.
gsd:ship
Create PR, run review, and prepare for merge after verification passes.
sddp-implement
Command description: Implement the current feature tasks. Argument hint: [optional: phase or task to start from] Command category: feature-delivery Prerequisites: spec, plan, tasks, checklists:complete-if-present.
mode
Show or switch the project's conformance mode between Enforced and À la carte, within the set the organization allows.