Borrowing it
Nothing to install: this file belongs to wanghao9610/STAR. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wanghao9610/STAR/main/.agents/skills/star-plan-executor/SKILL.mdgit clone --depth 1 https://github.com/wanghao9610/STARWrote 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/wanghao9610/star/star-plan-executor)<a href="https://agentmods.dev/skills/wanghao9610/star/star-plan-executor"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-plan-executor/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/wanghao9610/star/star-plan-executor"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-plan-executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 73 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00064 | $0.06394 |
| Opus 5.5 | $0.00026 | $0.02558 |
| Sonnet 5.5 | $0.00013 | $0.01279 |
| Haiku 4.5 | $0.00006 | $0.00639 |
Grade A, and why
star-plan-executor 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 14d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Plan Executor
Invocation: star-plan-executor PLAN_NAME [DESCRIPTION]. Resolve the leaf by slug, numeric prefix, or filename. Remaining natural language may constrain scope or explicitly authorize execution choices; ask only when the target, research scope, acceptance criteria, cost, key inputs, destructive action, or overwrite remains unresolved.
Shared conventions. Follow docs/mds/star-workflow/research-workflow-conventions.md for scope, authority, .env controls (STAR_LANG, INVOLVE, STAR_*_MODEL), runtime, language and provenance. Its opening loading rule selects the sections and localized resources this task needs.
Authorization context. Use the user's request or the parent run's recorded request, goal and limits as the scope for implementation. involve=low selects routine workflow choices within that scope. Accept auto=unattended only with the originating request described in conventions §10.7. Preserve host-required approvals and report a denied action while continuing independent authorized work. Apply the research-scope and source-material boundaries in the conventions opening, and distinguish technical failures from policy interventions under §10.8 before retrying or changing a model.
After resolving the target, run scripts/scan.sh --slim and treat its plan-frontmatter and run-log-frontmatter digest as raw input to Steps 0–1; still read the target leaf in full. If the script fails, read the plan files directly and report the fallback.
Passing a tier model. Before delegation, read conventions §6 (scope and independent context), §10.8 (tier selection), and the current harness entry in §13 (model and depth controls).
Analysis applicability. During finalization, follow .agents/skills/star-flow-status/references/source_state.md (Chinese: source_state_zh.md) to classify the actual run. Only verified engineering-only work may receive analysis: not applicable and an analysis-exemption binding in EXEC_LOG. Bind the current plans, EXEC_PLAN, changed source/configuration and raw check evidence; record after the last log/review/merge update. A later experimental scope or missing metric never inherits the exemption: record analysis as required and clear only its obsolete binding. Code review and completion/launch gates remain independent.
What ships with it
25 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.
- agents/openai.yaml 63 B
- assets/exec_log_template_zh.md 5.8 KB
- assets/exec_log_template.md 6.4 KB
- assets/exec_plan_template_zh.md 4.4 KB
- assets/exec_plan_template.md 4.7 KB
- references/agent_dispatch_spec_zh.md 6.6 KB
- references/agent_dispatch_spec.md 7.0 KB
- references/branch_rules_zh.md 12 KB
- references/branch_rules.md 13 KB
- references/design_check_zh.md 6.0 KB
- references/design_check.md 6.3 KB
- references/exec_rubric_zh.md 3.5 KB
- references/exec_rubric.md 3.8 KB
- references/orient_checklist_zh.md 2.4 KB
- references/orient_checklist.md 2.5 KB
- references/plan_sync_rules_zh.md 6.9 KB
- references/plan_sync_rules.md 7.6 KB
- references/resume_rules_zh.md 7.3 KB
- references/resume_rules.md 8.1 KB
- references/sizing_check_zh.md 1.9 KB
- references/sizing_check.md 1.8 KB
- references/stop_line_rules_zh.md 4.6 KB
- references/stop_line_rules.md 5.1 KB
- scripts/launch_state.sh 16 KB runs code
- scripts/scan.sh 25 KB runs code
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.
- 14d ago Changed · +3 lines db578cdd0df9
- 1mo ago Changed · +2 lines 7cf4d85aa4c6
- 1mo ago Changed · +7 tokens per session 5ca4ee4975ae
- 2mo ago Changed · -7 lines · -114 tokens per session 398ea7c5b770
- 2mo ago Changed a6bd1c305970
- 2mo ago First seen · 127 lines · 171 tokens per session scan A d01af948ec70
star-plan-executor is a skill published in the GitHub repository wanghao9610/STAR (54 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 6,394 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.
star-plan-executor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| star-plan-executorwanghao9610/STAR | Skill | 54 | 2d ago | MIT | A | 64 | Codex |
| create-workflowLazyAGI/LazyMind | Skill | 589 | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |
| task-prd-creatorcoco-research/coco | Skill | 785 | yesterday | Apache-2.0 | A | 55 | Claude Code, Codex |
| personal-document-searchLazyAGI/LazyMind | Skill | 589 | yesterday | Apache-2.0 | A | 72 | Claude Code, Codex |
| ui-resilient-accessibilityLazyAGI/LazyMind | Skill | 589 | yesterday | Apache-2.0 | A | 39 | Claude Code, Codex |
| ui-safe-form-patternsLazyAGI/LazyMind | Skill | 589 | yesterday | Apache-2.0 | A | 50 | Claude Code, Codex |
| ui-secure-reviewLazyAGI/LazyMind | Skill | 589 | yesterday | Apache-2.0 | A | 51 | Claude Code, Codex |