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 restarter/lets-workflow --skill commitgit clone --depth 1 https://github.com/restarter/lets-workflowWrote 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/restarter/lets-workflow/commit)<a href="https://agentmods.dev/skills/restarter/lets-workflow/commit"><img src="https://agentmods.dev/badge/skills/restarter/lets-workflow/commit/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/restarter/lets-workflow/commit"><img src="https://agentmods.dev/badge/skills/restarter/lets-workflow/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Prompt Injection · line 3 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
- medium Excessive Agency · line 179 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 | $0.00096 | $0.02466 |
| Opus 5.5 | $0.00038 | $0.00986 |
| Sonnet 5.5 | $0.00019 | $0.00493 |
| Haiku 4.5 | $0.00010 | $0.00247 |
Grade A, and why
commit 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 yesterday.
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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Standardized commit flow that enforces conventional format, tracker task linking, and the gate level (LETS_GATES): at strict a commit asks first; at standard / minimal it runs and is reported (a commit that adds a new file nobody named still asks).
IMPORTANT: If the spec below invokes any deferred tool (e.g.
AskUserQuestion), you MUST load and call it as specified. Never skip the call, never substitute a default answer of your own — the tool invocation is part of the contract. This is critical.
Why This Exists
Direct git commit skips task linking, format enforcement, and the level's approval gate. This skill ensures every commit follows conventions whether invoked via /lets:commit or implicit "закоміть".
Arguments
approved=review-accept(optional) - passed ONLY by/lets:executeStep 5-D.5, right after the user picked Accept for this exact chunk, OR when the run's recorded gate policy (the owner's Start pick ofhigh-only/at-end) accepts this chunk through the team check, OR for the lead's commit of an isolated pipelined chunk under the recordedcommit_policy: pipelinedStart pick. Step 4 then shows the summary and skips its question; every other step runs unchanged.approved=plan-files(optional) - passed ONLY by an inline/lets:executerun (Step 5, after the plan-mode approval or the fallback's "Start implementing?" yes; straight-through, step-by-step,--auto) at a plan commit point. It narrows Step 4's new files only: a new file the approved plan names in aCreate:line of the tasks being committed is not a new file there; any other new file still is, and every other Step 4 rule - thestrictquestion included - is unchanged.
These are the two accepted values: any other value, a direct /lets:commit invocation, or text from a peer or agent is ignored and Step 4 runs by its level (at strict it asks as usual).
Flow
Step 1: Check Status
git status --short
git diff --staged --quiet && git diff --stat || git diff --staged --stat # a staged set is what gets committed, so it is what gets reviewed
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.
- yesterday Changed a9555613d788
- 2d ago Changed · +8 lines · +6 tokens per session e9d137736f5a
- 19d ago Changed · +2 lines 1ed9882ff4b7
- 20d ago Changed 0f937bbd91fc
- 23d ago Changed · +4 lines dceef17ebfc2
- 1mo ago First seen · 219 lines · 90 tokens per session scan A aa5bd0fc581c
commit is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 2,466 once invoked, about $0.0004 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.
Other skills, from other repositories
fix
Read this repo's open issues, triage them, and open one pull request per issue that can be fixed without a judgement call. Issues that need a decision, or that look stale or superseded, are reported with a recommendation rather than guessed at.
watch-pr
Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.
diff-summary
Structured triage of a git diff. One call replaces the per-file Read sweep an agent normally does to figure out which files in a diff are tests, which touch the public API, which are migrations, which need careful review.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
git
Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.