Borrowing it
Nothing to install: this file belongs to webjsdev/webjs. 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/webjsdev/webjs/main/.claude/skills/webjs-start-work/SKILL.mdgit clone --depth 1 https://github.com/webjsdev/webjsWrote 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/webjsdev/webjs/webjs-start-work)<a href="https://agentmods.dev/skills/webjsdev/webjs/webjs-start-work"><img src="https://agentmods.dev/badge/skills/webjsdev/webjs/webjs-start-work/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/webjsdev/webjs/webjs-start-work"><img src="https://agentmods.dev/badge/skills/webjsdev/webjs/webjs-start-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 MCP Rug Pull · line 167 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 342 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.
- medium Excessive Agency · line 344 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 | $0.00036 | $0.13657 |
| Opus 5.5 | $0.00014 | $0.05463 |
| Sonnet 5.5 | $0.00007 | $0.02731 |
| Haiku 4.5 | $0.00004 | $0.01366 |
Grade A, and why
webjs-start-work 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 12d 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start work on a webjs GitHub issue
The webjsdev/webjs project tracks work on the GitHub Project board at https://github.com/orgs/webjsdev/projects/1. This skill runs the start-of-work lifecycle whenever the user wants to begin a tracked issue.
Precondition: the work MUST already have a tracked issue
This skill picks up from an EXISTING issue. Before running any step below, confirm the task has one. It often does NOT: a task that arrives from a conversation, a code-review finding, a dogfood observation, or your own idea has no issue yet, and THAT is the gap this guards.
If there is no tracked issue for this work, STOP. Do not create a branch, do not write code. First invoke webjs-file-issue to file it and capture the new number, THEN run this skill with that number. Starting code on untracked work is a process failure: the PR ships with no Closes #N, the work never appears on the board, and the card never moves to Done. This has happened (a whole feature was implemented and merged before any issue existed, then filed retroactively only after the user noticed).
If you are unsure whether an issue already exists, search before filing:
gh api "search/issues?q=repo:webjsdev/webjs+is:issue+<keywords>&per_page=20" \
--jq '.items[] | "#\(.number) [\(.state)] \(.title)"'
Search the ISSUES over REST rather than dumping the board. It matches bodies as
well as titles, so it is the better duplicate check, and it costs nothing from
the GraphQL budget. See .claude/gh-budget.md.
When in doubt, file it. A duplicate is cheap to close; untracked work is the expensive failure. Only once an issue number exists do you continue to Inputs below.
Inputs
The user's request typically names an issue by number (e.g. #112) or by description (e.g. "the dist issue"). Resolve the number first:
- If the user said
#Nexplicitly, use N. - If they described the issue by topic, search the issues over REST and match against titles. If multiple match, ask the user to disambiguate.
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.
- 12d ago Changed 28cab9a12c7a
- 13d ago Changed 799314c70873
- 28d ago Changed 389edacce9ff
- 1mo ago Changed 64bac48654eb
- 1mo ago Changed 7193987eab9d
- 1mo ago First seen · 361 lines · 36 tokens per session scan A 3644c01633f4
webjs-start-work is a skill published in the GitHub repository webjsdev/webjs (27 stars, last pushed 13d ago), licensed MIT. It adds 36 tokens to every session and 13,657 once invoked, about $0.0001 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
parallel-work-check
Apply before starting work on an existing branch. Checks for parallel work by other agents or developers that may supersede or conflict with your planned changes. Prevents wasted effort on stale branches.
github-issues
Create, search, triage, label, assign, comment on, and close GitHub issues using the gh CLI, with a curl REST fallback.
factory-handoff
Hand one exact agent-ready ticket to the central Factory runtime over the configured SSH forced-command boundary. Use when an operator asks to hand off an existing ticket or a prose request instead of implementing it in the current session.
github
A guide to using GitHub CLI, a command-line tool for working with GitHub repositories. It covers issues, pull requests, releases, labels, milestones, and workflow runs.
github
REST API access to repos, PRs, issues, and notifications.
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.