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 skills add XAIHT/Tlamatini --skill tlamatini_flw_doctorgit clone --depth 1 https://github.com/XAIHT/TlamatiniWrote 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/skills/xaiht/tlamatini/tlamatini_flw_doctor)<a href="https://agentmods.dev/skills/xaiht/tlamatini/tlamatini_flw_doctor"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/tlamatini_flw_doctor/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/skills/xaiht/tlamatini/tlamatini_flw_doctor"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/tlamatini_flw_doctor.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 | $0.00038 | $0.00605 |
| Opus 5 | $0.00019 | $0.00302 |
| Sonnet 5 | $0.00008 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
tlamatini-flw-doctor 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 12d 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.
What it actually says
.flw doctor
Statically validate a .flw file.
Checks:
- JSON parses; required keys present (
version,agents,connections). - Every node's
typeis a known agent type (mirrors the agent-folder list). - Every connection's
fromandtoreference real node ids. - No
target_agentsconnection points at Stopper / Ender / Cleaner — those useoutput_agentsper the agent contract. - Parametrizer nodes have at most one inbound and one outbound
target_agentsedge (single-lane queue invariant). - Terminal agents (Emailer / Notifier / RecMailer / Monitor-*)
have NO outbound
target_agents. - Logic gates: OR / AND have exactly 2 inbound source connections;
Barrier has N>=2; Asker / Forker have exactly 2 outbound branches
(
target_agents_a/target_agents_b); Counter has 2 (target_agents_l/target_agents_g).
Return { ok, problems: [{node_id, kind, message}, ...], summary }.
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.
- 12d ago First seen · 62 lines · 38 tokens per session scan A 49d68316f4e9
tlamatini-flw-doctor is a skill published in the GitHub repository XAIHT/Tlamatini (16 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 605 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 2026-08-30.
Other skills, from other repositories
grade-and-fix-daedalus
How to grade a Daedalus run (or pasted agent transcript), root-cause the failure, and ship the fix to Daedalus CORE as a stacked PR — without modifying the prompt-vault sandbox (read-only grading). Covers recurring bug archetypes (Unicode punctuation patch mismatch, syntax-vs-type mislabel, emoji box misalignment…
fix-typescript-build
How to fix a failing tsc/npm run build (type-check) run in a project, batching fixes into sprints to preserve context.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
cvm-ai-doctor
A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
code-search
Search a codebase efficiently with ripgrep regular expressions, file globs, and git history search. Use to locate symbols, usages, and definitions instead of reading whole files.