Borrowing it
Nothing to install: this file belongs to codervisor/leanspec. 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/codervisor/leanspec/main/.agents/skills/leanspec-pre-push/SKILL.mdgit clone --depth 1 https://github.com/codervisor/leanspecWrote 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/codervisor/leanspec/leanspec-pre-push)<a href="https://agentmods.dev/skills/codervisor/leanspec/leanspec-pre-push"><img src="https://agentmods.dev/badge/skills/codervisor/leanspec/leanspec-pre-push/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/codervisor/leanspec/leanspec-pre-push"><img src="https://agentmods.dev/badge/skills/codervisor/leanspec/leanspec-pre-push.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Tool Misuse · line 60 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 152 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Agent Snooping · line 169 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 173 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00129 | $0.02532 |
| Opus 5.5 | $0.00052 | $0.01013 |
| Sonnet 5.5 | $0.00026 | $0.00506 |
| Haiku 4.5 | $0.00013 | $0.00253 |
Grade A, and why
leanspec-pre-push 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 2mo 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
leanspec-pre-push
Mechanical checklist that catches the reviewer / CI failures this repo has actually had, plus a spec-link check that enforces the SDD loop locally.
This is lean-spec's analogue of onsager-pre-push / duhem-pre-push. The discipline is the same; the toolchain checks are lean-spec's (pnpm + cargo). The repo-specific patterns below come from this monorepo's structure (TypeScript packages, Rust crates, i18n locale files, schemas).
Why
CI on pull_request checks out a merge of origin/main + the PR branch, not the branch alone. Local pnpm typecheck without that merge is insufficient.
The spec-link step enforces "no PR without a spec or a trivial label" at push time, before the PR is open — so the author sees the problem locally instead of hearing about it from a reviewer.
Steps
Run all of these from the repo root.
1. Sync main into the branch
git fetch origin main
git merge origin/main --no-edit
Resolve conflicts locally, before push — never on the PR "Resolve conflicts" web editor (it bypasses any local validation). If the merge aborts cleanly, skip to step 2.
Resolving conflicts
-
Inventory what conflicted:
git status --short # U* lines = unresolved paths git diff --name-only --diff-filter=U -
Work by pattern, not by file. A single logical conflict often spans several files. Match what you see against the patterns below before touching conflict markers — the right fix is often "take main's version and re-apply your change on top", not a line-by-line merge.
-
Resolve, then stage each resolved path with
git add <path>. Re-rungit statusuntil noU*entries remain. -
Verify before committing the merge. Run
pnpm typecheck && pnpm pre-push. Runpnpm testfor the affected packages. If the merge touched Rust, also runpnpm build:rustandpnpm test:rust. -
Only then:
git commit --no-edit # default "Merge branch 'main' ..." message
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.
- 2mo ago First seen · 174 lines · 129 tokens per session scan A 6562fec49ed5
leanspec-pre-push is a skill published in the GitHub repository codervisor/leanspec (300 stars, last pushed 5mo ago), licensed MIT. It adds 129 tokens to every session and 2,532 once invoked, about $0.0005 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.
leanspec-pre-push compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| leanspec-pre-pushcodervisor/leanspec | Skill | 300 | 5mo ago | MIT | A | 129 | Claude Code, Codex |
| add-community-extensiongithub/spec-kit | Skill | 148k | yesterday | MIT | A | 63 | Claude Code |
| ax-extract-workflowsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 35 | Claude Code |
| gsd-quick-batchopen-gsd/gsd-core | Skill | 11k | yesterday | MIT | A | 32 | Claude Code |
| gsd-workspaceopen-gsd/gsd-core | Skill | 11k | yesterday | MIT | A | 20 | Claude Code |
| gsd-inboxopen-gsd/gsd-core | Skill | 11k | yesterday | MIT | A | 23 | Claude Code |
| gsd-pause-workopen-gsd/gsd-core | Skill | 11k | yesterday | MIT | A | 16 | Claude Code |