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 skills add btspoony/mstar-harness --skill mstar-iterationgit 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/skills/btspoony/mstar-harness/mstar-iteration)<a href="https://agentmods.dev/skills/btspoony/mstar-harness/mstar-iteration"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-iteration/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/skills/btspoony/mstar-harness/mstar-iteration"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-iteration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.05300 |
| Opus 5.5 | $0.00018 | $0.02120 |
| Sonnet 5.5 | $0.00009 | $0.01060 |
| Haiku 4.5 | $0.00005 | $0.00530 |
Grade A, and why
mstar-iteration 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 13d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mstar-iteration(迭代管理)
Load order
Read mstar-harness-core first. Path symbols → mstar-conventions. Per-plan gates → mstar-phase-gates. Knowledge crystallization → mstar-compound. Phase 2 implement 波次(进入 per-plan implement 前)→ mstar-sdd + mstar-dispatch-gates;Phase 2 QC 前 → mstar-review-qc。Git/worktree 载体(有 git 写或 lease 时)→ mstar-branch-worktree。Phase 1 角色派发 preflight(每次 invoke 前的 assignment preflight;enforcement: hard fail-fast)→ references/command-shared-invariants.md(本 skill 直接触发时不依赖 command 层)。On conflict, mstar-harness-core wins.
Phase 1 roadmap/milestone reads and Phase 3 close updates → mstar-project-governance, the sole owner of project roadmap/milestone read/write rules.
Phase detail 不在本 skill 正文:按下方 Phase route map 只加载当前动作对应的一行 detail——禁止无条件通读全部 phase references。
The primary coordinator owns all rows of the selected iteration and dispatches ordinary leaf tasks. Row configuration remains revisable during active execution; progress records the start and review states, and direct complete verifies QC/QA and the actual serial merge before writing Done. No row-specific PM launch or binding is required. Command entry accepts no arguments; reject nonempty arguments instead of broadening their scope.
设计思路
mstar 实践模式通常是:一次迭代锁定几个 spec 点(specify + clarify),产生多个 plan,每个 plan 含多个 tasks。per-plan 生命周期有完整的闭环(Prepare → Execute → QC → Done)。Compound 不是 per-plan 活动——它是迭代级收口,在迭代内所有 plan Done 后,沉淀一轮知识。
本 skill 管理迭代 Phase 1–6(command 层可聚合编排,但 不得反向引用 command 名;第三方 helper 仅由 command 按需发现):
Phase 1: start
↓
Phase 2: Autonomous Execute —— [per-plan lifecycle × N]
↓
Phase 3: iteration-close
↓
Phase 4: PR delivery(开 PR)
↓
Phase 5: PR merge-ready loop —— 至 mergeable + CI 全绿 + reviews resolved
├ reviewed-auto:跑 PR 级 review loop(mstar-pr-loop)→ 当前 head 上 settled、已 posted 的 ship it,**并且**(仅当存在挂载的外部 review bot;无 bot 时记 N/A)外部 AI review(§5.1b)在当前 head 达到其通过线(Greptile 5/5)、不失败、无 blocking finding = merge 授权
└ owner-gated:停在 merge-ready → 等人类 owner 对当前 PR head 的书面批准
↓
Phase 6: post-merge close —— merge 授权完成、PR merged 后 §6.1–§6.4
↓
迭代交付完成
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/autonomous-direction-lock.md 6.5 KB
- references/command-shared-invariants.md 5.8 KB
- references/iteration-artifact-boundaries.md 8.8 KB
- references/iteration-compass-template.md 7.8 KB
- references/iteration-corpus-hygiene.md 3.4 KB
- references/iteration-workspace-readme-template.md 1.7 KB
- references/phase-1-prepare.md 31 KB
- references/phase-2-worktree-lease.md 30 KB
- references/phase-3-iteration-close.md 13 KB
- references/phase-4-5-pr-delivery.md 16 KB
- references/phase-6-post-merge-close.md 8.1 KB
- references/phase5-helper-discovery.md 2.4 KB
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.
- 13d ago Changed dcd63b7d9478
- 14d ago Changed · +4 lines 93e6cc65b44b
- 16d ago Changed · -76 tokens per session 9e8fcb4f3ab4
- 17d ago Changed · +1 lines 142b5a2c1e52
- 19d ago Changed · +2 lines b7c766a7aaf2
- 27d ago Changed · -7 tokens per session fb95a180cfb4
- 1mo ago Changed · -10 lines 60e90254c56f
- 1mo ago Changed · +7 tokens per session bfc9a87e75ed
- 1mo ago Changed 3550bfd0020f
- 1mo ago First seen · 141 lines · 121 tokens per session scan A d7de61cd5f0f
mstar-iteration is a skill published in the GitHub repository btspoony/mstar-harness (68 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 5,300 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.
mstar-iteration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mstar-iterationbtspoony/mstar-harness | Skill | 68 | 2d ago | MIT | A | 45 | Claude Code |
| comet-openrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 33 | Codex |
| subagent-driven-developmentrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 17 | Claude Code, Codex |
| comet-buildrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 36 | Claude Code, Codex |
| cometrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 44 | Claude Code, Codex |
| comet-classicrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 48 | Codex |
| comet-designrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 29 | Claude Code, Codex |