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 chekusu/wanman --skill wanman-cligit clone --depth 1 https://github.com/chekusu/wanmanWrote 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/chekusu/wanman/wanman-cli)<a href="https://agentmods.dev/skills/chekusu/wanman/wanman-cli"><img src="https://agentmods.dev/badge/skills/chekusu/wanman/wanman-cli/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/chekusu/wanman/wanman-cli"><img src="https://agentmods.dev/badge/skills/chekusu/wanman/wanman-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.00937 |
| Opus 5.5 | $0.00008 | $0.00375 |
| Sonnet 5.5 | $0.00004 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
wanman-cli 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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wanman CLI
You are running inside the wanman Agent Matrix. Use the following CLI commands to collaborate with other agents.
Startup Protocol
On every startup, execute in order:
cat ./CLAUDE.md— Read your role guidewanman recv— Check for pending messageswanman task list --assignee $WANMAN_AGENT_NAME— View tasks assigned to you
Messages
| Command | Description |
|---|---|
wanman send <agent> "<message>" |
Send a normal message |
wanman send <agent> "<message>" --steer |
Urgent message (interrupts the target agent's current work) |
wanman send human --type decision "<message>" |
Ask the human to make a decision |
wanman send human --type blocker "<message>" |
Tell the human what is blocking progress |
wanman recv |
Receive pending messages |
wanman escalate "<message>" |
Escalate to the CEO agent |
Note: --steer forcefully interrupts the target agent's process and restarts it. Use only in urgent situations.
Prefer explicit --type decision|blocker when sending to human, so the product can render the right card.
Tasks
wanman task create "<title>" --assign <agent> [--priority 1-10] [--after id1,id2] [--desc "<description>"]
wanman task list [--status <pending|in_progress|done|blocked>] [--assignee <agent>]
wanman task get <id>
wanman task update <id> --status <in_progress|blocked|done> [--result "<text>"]
wanman task done <id> "<result>"
--after: Declare dependencies (comma-separated task IDs); the task will not execute until dependencies are complete--priority: 1 = highest, 10 = lowesttask doneis a shortcut fortask update --status done --result
Artifacts (Structured Outputs)
wanman artifact put --kind <kind> --path "<domain>/<category>/<item>" \
--source "<source>" --confidence <0-1> [--task <id>] [--file <path>] '<metadata json>'
wanman artifact list [--agent <a>] [--kind <k>]
wanman artifact get <id>
--file: Store file contents in the database (version-controlled storage)--source: Information source, e.g.,web_search:site.com,estimate,official_data--confidence: 0.3-0.5 (estimate) | 0.6-0.8 (data-backed) | 0.9+ (authoritative source)
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.
- 1mo ago First seen · 97 lines · 19 tokens per session scan A 3c00aeaa2d5a
wanman-cli is a skill published in the GitHub repository chekusu/wanman (694 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 937 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 2026-08-30.
Other skills, from other repositories
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
paper-abstract-author
Write the abstract after the paper body has been revised, using the final claims and evidence.
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.