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 instructions/joelbondoux/work-timer/claude-mdgit clone --depth 1 https://github.com/JoelBondoux/Work-TimerWhat 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 | $0.00801 | $0.00801 |
| Opus 5 | $0.00400 | $0.00400 |
| Sonnet 5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
Work-Timer CLAUDE.md 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Instructions for Work-Timer
Repository Workflow
masteris the production-ready branch.- Do not commit feature work directly to
master. - Create short-lived task branches from
master. - Submit a PR back to
master. - Ensure
npm testandnpm run buildpass before merge. - Prefer squash merge.
Branch Naming
feature/<short-description>fix/<short-description>chore/<short-description>
Contribution Standards
- Keep PRs scoped to one concern.
- Add tests for logic changes.
- Update docs for user-facing changes.
- For user-facing PowerShell/terminal output formatting, follow
docs/powershell-output-style-guide.mdas the default standard for current and future output UX changes.
Safety And Security First Policy
- Treat user data protection, billing correctness, and destructive-operation safety as top priority over speed.
- Default to least-privilege and non-destructive behavior: prefer dry-run, explicit confirmations, and reversible changes.
- Never weaken or bypass safety checks, authorization boundaries, or validation logic unless explicitly required and documented.
- If a change introduces meaningful security, privacy, or integrity risk, stop and escalate with options, risks, and a recommended safe default.
- Call out security-impacting changes in PR summaries and include focused validation steps.
Local Staging Workspace Rules
- Use
staging/for local-only test notes, debug helpers, and temporary artifacts. - Treat
staging/as non-production and non-release content. - Do not commit files from
staging/. - Do not reference
staging/as a required documentation location; durable docs must live underdocs/.
Required Validation
- Run
npm testandnpm run buildbefore opening or updating a PR. - Run
npm run check:productionto block debug/dev-only artifacts from release branches. - If files in
src/are changed, regenerate and commit matchingdist/outputs when applicable. - If CLI behavior changes, update
docs/cli-reference.mdand related setup/readme docs. - If MCP tools are added or changed, update
docs/mcp-tools.mdto keep tool docs and counts accurate.
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 · 83 lines · 801 tokens per session scan A f6887f51f475
Work-Timer CLAUDE.md is an instructions file published in the GitHub repository JoelBondoux/Work-Timer (0 stars, last pushed 9d ago), licensed MIT. It adds 801 tokens to every session, about $0.0040 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.