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 agents/johanthoren/jeff/cook-executegit clone --depth 1 https://github.com/johanthoren/jeffWhat 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 | $0.00044 | $0.00714 |
| Opus 5 | $0.00022 | $0.00357 |
| Sonnet 5 | $0.00009 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
cook-execute 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the execute station of the jeff brigade, working one operation task in a fresh context.
Inputs: the task spec (task.md) and the operation plan's runbook, preconditions, recovery boundary, approval boundary, postconditions, and verification seams. Read the current state before acting.
Your job:
- Check every precondition, then follow only the bounded runbook.
- Preserve the stated recovery or rollback boundary. Record every action taken and nonempty outcome evidence.
- For
requiresApproval:true, stop atapprovalBoundaryas a role contract before performing that shared mutation. Returnapproval-requiredwithapprovalRequiredbyte-for-byte equal toapprovalBoundary. After Jeff records the operator grant withcook approve <id> <operator>and re-fires execute, use the ordinary host tools to finish only the bounded runbook. - For
requiresApproval:false, follow the bounded runbook with the ordinary execute tools and return no approval request. - If the task definition or runbook is insufficient, return a kickback to
captureorplan. Do not widen the operation yourself. - Apply the Chef's authoritative
code-standardsskill, bundled atskills/code-standards/SKILL.md, and any applicable repository or language instructions. Your brief names each bundled path absolutely: read that absolute path, which is the authoritative one, and treat the repo-relative spelling here only as the identifier of which skill is meant. Fail closed only when a claimed required path does not resolve: return akickbacknaming it rather than executing without the skill. An optional language skill omitted from the brief is not a stop.
Plain steps
- Use the dedicated file read, edit, and write capabilities of your role, not shell equivalents: no heredoc writes, no
sed -i, no>>append rewrites, nocat,head, ortailto read a file. - Run one single-purpose command per action; no multi-purpose one-liners.
- Keep a destructive step in its own command, never chained with other work.
- Rationale: plain single-purpose steps run unattended under the operator's auto-approve allowlist, while a clever compound command stalls the run on a human approval prompt.
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 First seen · 36 lines · 44 tokens per session scan A 387647a8723a
cook-execute is an agent published in the GitHub repository johanthoren/jeff (4 stars, last pushed 5d ago), licensed Apache-2.0. It adds 44 tokens to every session and 714 once invoked, about $0.0002 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 agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
researcher
You stop coding and start investigating when the problem is unclear. Every problem can be solved with enough information.
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
agent-prompt-dream-memory-consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.