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 agentmods add skills/benwu95/prospec/submit-prnpx skills add benwu95/prospec --skill submit-prgit clone --depth 1 https://github.com/benwu95/prospecWhat 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 | $0.00059 | $0.02154 |
| Opus 5 | $0.00030 | $0.01077 |
| Sonnet 5 | $0.00012 | $0.00431 |
| Haiku 4.5 | $0.00006 | $0.00215 |
Grade A, and why
submit-pr 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit PR Skill
Open the pull request for a completed change: push its branch, write the body in the house format,
and link it to the issue the change registered. CONTRIBUTING.md → Submit a Pull Request is the
authority for these rules; this skill only executes them, so when the two disagree, that file wins
and this one is stale.
Language
The PR body is Traditional Chinese (Taiwan) — a house convention, deliberately not a
consequence of the Constitution's [MUST] Language Policy (that rule is defined over repo paths,
and a PR body is not one). The PR title mirrors the feature commit's subject and therefore stays
English, as do code, commit messages, and the trust zone inside the same PR (see
prospec/CONSTITUTION.md → Language Policy, mirrored in AGENTS.md).
Never append an AI attribution footer — not to the body, not to the commits. This repo carries no AI co-authorship anywhere.
Preconditions — do not open the PR until all hold
- The change is archived.
/prospec-archivehas run: REQs graduated, Knowledge synced,prospec/specs/_archived-history/{date}-{name}.mdwritten.prospec statusreporting the change as still in flight means this step is unfinished. - Both commits exist, in order — the feature commit (boundary:
/prospec-verifyat grade S/A, folding implementation + review fixes + verify fixes + module READMEs + re-derived counts), then the archive commit.CONTRIBUTING.md→ §4 Commit specifies both. - Green locally:
pnpm test,pnpm typecheck,pnpm lint,prospec check, andpnpm run counts:check(CI gates this one; a stale factual count fails the PR). Capture the numbers — the body reports them. ghis authenticated as an account with write access. With more than one account logged in, the active one can silently be the wrong one, andghthen fails with a misleading error.git pushmay travel over a different credential path (an SSH host alias) and succeed regardless, so a successful push proves nothing here:
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 First seen · 153 lines · 59 tokens per session scan A 06a4a3fdade5
submit-pr is a skill published in the GitHub repository benwu95/prospec (5 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 2,154 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ospec-goal
Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
review-spd
Findings-first code review workflow for AI coding agents. Use when the user asks to review uncommitted changes, commits in a date range, or a branch compared to the main branch / PR-style diff. Focuses on bugs, regressions, correctness risks, missing tests, security/data-safety issues, and other behavior-changing…
deep-discuss
结构化深度讨论 Skill，用于与用户进行多轮问题分析和方案设计。当用户描述一个问题现象、故障表现、 技术困惑、方案选择困难，或明确说"讨论一下"、"帮我分析"、"我遇到一个问题"、"你觉得怎么样"、 "帮我想想"、"我在纠结"时，必须使用本 skill。当用户提供了一段描述（可能附带截图）并期望深入分析 而非直接给答案时，也应触发本 skill。即使用户只是抛出一个现象描述没有明确提问，也要使用本 skill 来引导结构化思考。不要在简单的事实查询（"X是什么"）或明确的执行指令（"帮我写个脚本"）上触发。.
spec-driven-develop
Automates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migrate", "overhaul", "refactor entire project", "transform", "rebuild in [language]", "spec-driven", or describes any large-scale project transformation that requires planning before coding. Also triggers on…