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-issuenpx skills add benwu95/prospec --skill submit-issuegit 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 | $0.00077 | $0.01700 |
| Opus 5 | $0.00039 | $0.00850 |
| Sonnet 5 | $0.00015 | $0.00340 |
| Haiku 4.5 | $0.00008 | $0.00170 |
Grade A, and why
submit-issue 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit Issue Skill
Open a GitHub issue for the prospec repo in the house format. The format below is derived from the merged issue corpus (#179–#196, #203–#208); this skill executes the pattern, and newer merged issues outrank it when they disagree.
Language
The issue body is Traditional Chinese (Taiwan) — a house convention, same rationale as PR bodies:
the Constitution's [MUST] Language Policy is defined over repo paths, and an issue body is not one
(see prospec/CONSTITUTION.md → Language Policy, mirrored in AGENTS.md). The title stays
English in conventional-commit form, as do code identifiers, file paths, and technical terms inside
the body. Never append an AI attribution footer. The repo uses no labels — do not add any.
Scope discipline — one issue per change
Size each issue so it maps to exactly one prospec change / one PR (/prospec-new-story registers
it via prospec change story --issue "#NN"). A body that needs two unrelated 方案 groups or two
independent AC sets is two issues — split them and cross-link the series. Defects discovered
mid-flight go to a change artifact or a new issue, never into frozen planning docs.
Preconditions
-
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:gh api user -q .login # must be able to write to this repo gh auth switch --hostname github.com --user <account> # only if it is not -
Evidence in hand. Every number, file path, and behavioral claim in the body must come from something actually observed — a measurement, an archived record, a review finding, a repro run.
Step-by-step
1. Draft the body to a scratch file
Write it somewhere git-ignored (e.g. .tasks/issue-<slug>.md or the session scratchpad), following
the format below. Show the draft for sign-off before creating unless the user already approved
the content in conversation — an issue is public the moment it exists.
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 · 128 lines · 77 tokens per session scan A 559a3702b93d
submit-issue is a skill published in the GitHub repository benwu95/prospec (5 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 1,700 once invoked, about $0.0004 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…