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/pounceai/bob-control/claude-mdgit clone --depth 1 https://github.com/PounceAI/bob-controlWrote 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/instructions/pounceai/bob-control/claude-md)<a href="https://agentmods.dev/instructions/pounceai/bob-control/claude-md"><img src="https://agentmods.dev/badge/instructions/pounceai/bob-control/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00629 | $0.00629 |
| Opus 5 | $0.00315 | $0.00315 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
bob-control CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repo with Claude Code
Bob Control is an MCP server + CLI + auto-dispatch worker over a SQLite
task board (data/tasks.db). Bob runs on native Windows and holds the board open in WAL.
Two execution contexts
Claude Code here runs in one of two contexts. Detect which by uname / whether wslpath
exists, and use the matching commands.
WSL inside Bob (common case)
The board is held open in WAL by Bob on the Windows side. WAL's shared memory can't cross
the WSL/Windows boundary, so opening the board with Linux-side node fails with
disk I/O error 4618 — even a read. Don't try to fix that by changing the journal mode;
it can't be converted while Bob holds it, and WAL is correct for Bob.
Instead, reach the board through Windows node.exe (available via WSL interop):
- Board ops:
./bob <create|list|show|...>— the shim routes the CLI throughnode.exe. - Make Bob execute a queued task (dispatch over Bob's IPC pipe, which only a Windows-side
process can reach):
node.exe "$(wslpath -w dist/worker.js)" --once. - Build (plain file I/O, runs fine under Linux node):
npm run build.
Native Windows
No boundary, so the plain scripts work directly: node dist/cli.js ..., npm run worker,
npm run build. The ./bob shim also works here (it falls back to plain node).
Quality gate
Before pushing or opening a PR, run the same checks CI enforces and make sure they're green:
npm run lint && npm run format:check && npm test
(npm run format auto-fixes formatting.) CI runs lint → format:check → build → test+coverage on
Windows for Node 22 and 24; a red check blocks the merge.
PR & commit messages
Substance only: the problem, the changes, why. No process narration ("did a deslop pass", "ran two reviews", "added tests"), no validation play-by-play, no AI-attribution trailer.
Worktrees (run several in parallel)
Several worktrees of this repo can run in parallel on one shared board: one Bob window + one
worker per worktree, each pinned --tag worktree:<name>, board shared via BOB_TASKS_WORKTREE_SHARED=1.
Launch a per-worktree Bob with launch-bob.cmd <worktree-path>; a per-worktree lease keeps one worker
per checkout. Full runbook (and the Bob-1.x-only caveat): README → Worktrees.
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.
- 4d ago First seen · 57 lines · 629 tokens per session scan A ad09c28b91f0
bob-control CLAUDE.md is an instructions file published in the GitHub repository PounceAI/bob-control (1 stars, last pushed 20d ago), licensed Apache-2.0. It adds 629 tokens to every session, about $0.0031 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
kraken AGENTS.md
Instructions for rafael-adcp/kraken, covering agents.md — running as a kraken tentacle, your operating contract — read these, then follow them, why there are no deltas any more and driving it non-interactively.
ai-literacy-superpowers copilot-instructions.md
Copilot instructions for Habitat-Thinking/ai-literacy-superpowers, covering project conventions and constraints, stack, naming, file structure and error handling.
kraken CLAUDE.md
Instructions for rafael-adcp/kraken: This project has a knowledge graph at graphify-out/ with god nodes, community structure, and cross-file relationships.
matilha-skills GEMINI.md
Instructions for danilods/matilha-skills, covering matilha — cognitive + methodological harness, how this loads in gemini cli, phases (0-70), companion detection and tool mapping.
AI-Prompt-Guide-MCP CLAUDE.md
Claude Code instructions for Blakeem/AI-Prompt-Guide-MCP, a project described as: Deprecated. MCP server and Claude Code plugin with task driven agent orchestration workflows, guides, markdown knowledge graphs, with intelligent context injection.
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).