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 | $0.00112 | $0.03604 |
| Opus 5 | $0.00056 | $0.01802 |
| Sonnet 5 | $0.00022 | $0.00721 |
| Haiku 4.5 | $0.00011 | $0.00360 |
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 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 — 123 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 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。
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 1–5(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
↓
迭代交付完成
关键定位:
- Phase 3 在 integration 分支收口 compound / roadmap;开 PR(Phase 4)≠ 迭代交付完成。
- Phase 5 是 merge-ready loop(修复 → 等 CI/review 波次结束再 push → 再验证,至 §5.5 exit);Loop 理念与 push cadence SSOT 在本 skill(§2.6;push cadence 细则 §5.1a →
references/phase-4-5-pr-delivery.md);宿主 command 可叠加额外 non-mstar-*helper(优先babysit/*-babysit;greploop可选),但不写入mstar-*load order。 - 一次迭代 = 一个 PR;compound 产物随 PR 合入 snapshot
branch.target。
Phase route map(唯一路由表 — 按当前动作加载)
| 当前动作 | 必读 detail(按需加载,勿通读) |
|---|---|
| start(启动迭代 / 重开方向锁定) | references/phase-1-prepare.md(§1.1–§1.6:上下文、范围与 direction lock、compass、索引、v2 状态面、产物边界、§1.6 Review & Edit 链) |
| execute / resume(推进或恢复 per-plan 循环) | references/phase-2-worktree-lease.md(§2.0 五道闸、§2.1–§2.5 loop/dispatch 细则、control worktree + lease 全文) |
| close(全部 plan Done 后收口迭代) | references/phase-3-iteration-close.md(§3.0–§3.6:entry checklist、compound、roadmap、完成标记、exit checklist + commit) |
| PR / merge-ready(开 PR、推进合并就绪 loop) | references/phase-4-5-pr-delivery.md(§4–§5.2:开 PR、§5.1a push cadence、loop、exit checklist) |
| Phase 5 helper discovery(仅 command 层按需) | references/phase5-helper-discovery.md(babysit / greploop 发现) |
What ships with it
11 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 4.8 KB
- references/command-shared-invariants.md 4.0 KB
- references/iteration-artifact-boundaries.md 6.3 KB
- references/iteration-compass-template.md 5.0 KB
- references/iteration-corpus-hygiene.md 2.5 KB
- references/iteration-workspace-readme-template.md 1.1 KB
- references/phase-1-prepare.md 11 KB
- references/phase-2-worktree-lease.md 24 KB
- references/phase-3-iteration-close.md 8.6 KB
- references/phase-4-5-pr-delivery.md 6.3 KB
- references/phase5-helper-discovery.md 2.1 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.
- 2d ago Changed · -286 lines 5f20b4c1e105
- 7d ago Changed ca4e1e993c2f
- 11d ago First seen · 409 lines · 112 tokens per session scan A 4640e20c362a
mstar-iteration is a skill published in the GitHub repository btspoony/mstar-harness (58 stars, last pushed today), licensed MIT. It adds 112 tokens to every session and 3,604 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
comet-native
A workflow for managing Native changes in Comet, where requirements, progress, and acceptance results are saved in project files. It uses the Comet command-line runtime to move through defined work stages.
comet-build
A Comet workflow step for turning an approved design into an implementation plan and completed code changes. Comet is the project workflow system described by the add-on.
comet-classic
A Chinese-language workflow guide for starting or resuming a structured software change using OpenSpec and Superpowers.
comet-open
A guide for starting an OpenSpec change: a tracked software task with proposal, design, task, and state files. It also covers choosing or restoring the correct project workspace and output language.
comet-build
Comet Phase 3: Plan and Build. Invoke with /comet-build. Create plans and select execution method (subagent or direct) for implementation.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.