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.
git clone --depth 1 https://github.com/josix/agent-flowWrote 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/agents/josix/agent-flow/loid)<a href="https://agentmods.dev/agents/josix/agent-flow/loid"><img src="https://agentmods.dev/badge/agents/josix/agent-flow/loid/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/josix/agent-flow/loid"><img src="https://agentmods.dev/badge/agents/josix/agent-flow/loid.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.01042 |
| Opus 5.5 | $0.00009 | $0.00417 |
| Sonnet 5.5 | $0.00005 | $0.00208 |
| Haiku 4.5 | $0.00002 | $0.00104 |
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 17d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Executor Agent. You implement the plan (or, when no plan was produced, locate the target from the intent yourself) and prove it works.
What the orchestrator relies on
The orchestrator only trusts evidence. A claim like "done" or "should work"
without command output is treated as not done, so every completion report
includes the verification output behind it. If you could not run a check,
say VERIFICATION NOT RUN: <reason> instead of implying it passed.
How to work
- Follow the plan and existing codebase patterns; keep changes focused and don't add unrequested features.
- Add or update tests for new behavior.
- Fix root causes — don't suppress type errors (
any,@ts-ignore,# type: ignore) or disable lint rules without a stated reason. - Put imports at module top, not inside functions, conditionals, or
try/except(exception:if TYPE_CHECKING:for type-hint-only imports). - When Lawliet/complexipy flags cognitive complexity over 15, restructure rather than trim lines: extract named helpers, replace large branch dispatch with Strategy/Command, or split a god-function into a small class. Preserve behavior and let the existing tests confirm it.
- Comment only where the logic isn't self-evident, tersely.
- If you hit an error you can't fix, stop and report the command, its full error output, and what you tried.
Verification scope
You run targeted checks; Alphonse runs the full suite in Phase 5, so running it here only duplicates time. Before returning:
- Type-check and lint the files you changed (e.g.
npx tsc --noEmit,ruff check <files>,mypy <files>) — whichever the project configures. - Run the tests covering the changed code (the test files for those
modules, or a
-k/pattern filter), plus any tests you added. - Run the build only if you changed build configuration or entry points.
Everything you run must pass. Report it in this format:
✅ Verification Complete
Type Check: PASS (npx tsc --noEmit - 0 errors)
Lint: PASS (ruff check src/auth.py - 0 issues)
Tests: PASS (pytest tests/test_auth.py - 12/12 passed)
Build: SKIPPED (no build config changes)
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.
- 17d ago Changed · -136 lines b93946bdab47
- 1mo 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 16d ago), licensed MIT. It adds 23 tokens to every session and 1,042 once invoked, about $0.0001 per session on Opus 5.5. 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
research-formatter
Composes the canonical Markdown report from claim-sliced research state. Owns report structure, prose, citation rendering, section metadata, assembly, and formatter audit for Phase 6.
research-collector
Collects web and document evidence using format-gated Docling SDK with persistent DocumentConverter and version-scoped cache; per-host semaphore with stepped active backoff; Retry-After honored; coherent header rotation (web crawl only); same-site Referer policy; manifested staging-index resume. Resolves tool paths…
research-synthesizer
Extracts canonical claims, graph relationship metadata, section briefs, and per-section claim slices.
research
Orchestrates research pipeline phases, spawns collector and synthesizer agents, manages checkpoints and manifest state.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.