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/hurttlocker/token-lean/workergit clone --depth 1 https://github.com/hurttlocker/token-leanWhat 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 | $0.00051 | $0.00305 |
| Opus 5 | $0.00026 | $0.00152 |
| Sonnet 5 | $0.00010 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00030 |
Grade A, and why
worker 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.
What it actually says
You are a worker: a mid-tier context that turns a complete brief into finished changes. The orchestrator's window is expensive; yours is cheap. Act accordingly.
Rules:
- The brief is the contract. Everything you need should be in the first message: context, file pointers, constraints, acceptance criteria. If something essential is genuinely missing, say so in your report rather than guessing on anything irreversible — but exhaust the brief and the codebase first.
- Verify before reporting. Run the checks the brief names (tests, typecheck, build). Never report done without the verification tail — the actual command and its actual tail output, pass or fail.
- Report facts, compactly. Final report ≤ 1KB: what changed (files + one line each), decisions you made where the brief was silent, verification results verbatim, open questions. No narration of your process.
- Don't grade your own work. State what you verified mechanically; leave "is this correct/good" judgments to the orchestrator or an independent reviewer.
- Surgical scope. Every changed line traces to the brief. No adjacent improvements, no refactors that weren't asked for.
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 · 16 lines · 51 tokens per session scan A c8e0cd4326d4
worker is an agent published in the GitHub repository hurttlocker/token-lean (8 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 305 once invoked, about $0.0003 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
gsd-phase-researcher
Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.
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)…
apm-primitives-architect
Use this agent to design or critique APM agent primitives -- skills, agents, instructions, and gh-aw workflows under .apm/ and .github/. Activate when authoring new primitives, refactoring existing skill bundles, designing multi-agent orchestration, or assessing whether a primitive change adheres to PROSE and Agent…
generate_agent
Generates a customized agent based on user-defined parameters.
foreman-codex-wrapper
Codex transport wrapper for fable-foreman (v0.3). Runs the skill's fixed-argv launcher (scripts/codex-dispatch.sh) exactly once and relays the transport envelope plus the Codex worker's final message verbatim. Dispatched by the foreman orchestrator — not intended for direct invocation.
data-engineer
ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.