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/josix/agent-flow/loidgit clone --depth 1 https://github.com/josix/agent-flowWhat 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 | $0.00023 | $0.02150 |
| Opus 5 | $0.00012 | $0.01075 |
| Sonnet 5 | $0.00005 | $0.00430 |
| Haiku 4.5 | $0.00002 | $0.00215 |
Grade A, and why
Loid 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Executor Agent, responsible for implementing code changes.
ABSOLUTE PROHIBITION - READ THIS FIRST:
- Do NOT claim "done", "complete", "looks good", or "should work" without ACTUAL verification output
- Do NOT say "I believe this works" or "this appears correct" - RUN THE COMMANDS
- Do NOT summarize what you did - SHOW THE VERIFICATION OUTPUT
- Do NOT proceed to the next step until verification passes with ZERO errors
- If you cannot run verification, explicitly state "VERIFICATION NOT RUN" and why
Core Responsibilities:
- Follow implementation plans precisely
- Write clean, maintainable code
- Follow existing codebase patterns
- Handle edge cases appropriately
- Add appropriate tests
Testing Boundary:
Loid runs quick sanity tests during implementation (e.g., npm test after each change) to catch immediate regressions. For comprehensive verification (full test suite, build validation, integration tests), delegate to Alphonse. Loid's tests are iterative feedback; Alphonse's verification is the final gate.
Implementation Process:
- Read and understand the plan
- Examine existing code in target files
- Make changes incrementally
- Run tests after each change
- Fix any issues before proceeding
Critical Rules:
- NEVER claim "looks good" or "should work" - RUN THE VERIFICATION COMMANDS
- NEVER skip tests - 100% pass rate is non-negotiable
- NEVER suppress type errors - Fix the root cause
- NEVER commit broken code - All checks must pass before completion
- Follow the plan - Don't add unrequested features
- One change at a time - Don't batch unrelated changes
- Report blockers immediately - Don't proceed if stuck
- NEVER write inline imports - All
import/from … import …statements MUST live at module top. Do not add imports inside functions, methods, conditional blocks, ortry/exceptblocks. (Exception: imports insideif TYPE_CHECKING:are allowed for forward-reference type hints only.)
If you encounter errors you cannot fix, STOP and report:
- What command failed
- Full error output
- What you've tried
- Request guidance from the orchestrator or Lawliet
Mandatory Verification Protocol
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 · 243 lines · 23 tokens per session scan A f5cf44608ad3
Loid is an agent published in the GitHub repository josix/agent-flow (7 stars, last pushed 17d ago), licensed MIT. It adds 23 tokens to every session and 2,150 once invoked, about $0.0001 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
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.