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 Tyox-all/Weave_Protocol --skill hundredmengit clone --depth 1 https://github.com/Tyox-all/Weave_ProtocolWrote 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/tyox-all/weave_protocol/hundredmen)<a href="https://agentmods.dev/skills/tyox-all/weave_protocol/hundredmen"><img src="https://agentmods.dev/badge/skills/tyox-all/weave_protocol/hundredmen/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/tyox-all/weave_protocol/hundredmen"><img src="https://agentmods.dev/badge/skills/tyox-all/weave_protocol/hundredmen.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 | $0.00116 | $0.00943 |
| Opus 5.5 | $0.00046 | $0.00377 |
| Sonnet 5.5 | $0.00023 | $0.00189 |
| Haiku 4.5 | $0.00012 | $0.00094 |
Grade A, and why
security-inspection 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hundredmen — Real-Time MCP Security Proxy
@weave_protocol/hundredmen intercepts MCP tool calls, analyzes them, and decides whether to allow, block, or require approval. v1.1.0 adds enforcement of WARD.md policies at the interception layer.
When to use
- User has an agent and wants visibility into what tools it's calling
- User wants to gate sensitive operations behind manual approval
- User has a WARD.md and wants it enforced at runtime, not just declared
- User suspects drift: "the agent said X but is doing Y"
- User wants reputation tracking for the MCP servers they use
Gating order
When a tool call hits Hundredmen, the checks run in this order:
- WARD policy (if loaded) — capability/filesystem/network rules from
WARD.md - Reputation — server trust score
- Intent / drift — declared vs actual comparison
- Manual approval — if any earlier gate produced
require_approval
WARD is the first gate. A WARD deny short-circuits everything else.
WARD-related tools
hundredmen_load_ward({ path? })— load a WARD.md (auto-loads./WARD.mdon startup)hundredmen_show_ward()— show currently active policyhundredmen_check_ward({ tool, args })— dry-run a tool call against the policyhundredmen_unload_ward()— disable WARD enforcement
Other key tools
hundredmen_create_session({ agent_id? })hundredmen_declare_intent({ session_id, intent })hundredmen_diff_intent({ session_id })hundredmen_get_live_feed({ since?, limit? })hundredmen_get_pending()/hundredmen_approve_call/hundredmen_block_callhundredmen_check_reputation({ server_id })hundredmen_get_stats()/hundredmen_get_server_stats({ server_id })
Decision rules
| User says | Action |
|---|---|
| "Set up monitoring for my agent" | hundredmen_create_session + hundredmen_declare_intent |
| "What is my agent doing right now" | hundredmen_get_live_feed |
| "Why was this call blocked" | hundredmen_show_ward + check live feed for the blocked call |
| "Will my WARD block X" | hundredmen_check_ward({ tool: 'X', args: {...} }) |
| "I want WARD enforcement on" | hundredmen_load_ward() (loads from CWD or env) |
| "This server seems off" | hundredmen_check_reputation + hundredmen_report_suspicious |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 69 lines · 116 tokens per session scan A b2a69f726e73
security-inspection is a skill published in the GitHub repository Tyox-all/Weave_Protocol (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 943 once invoked, about $0.0005 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 skills, from other repositories
ui5wc-upgrade
Guide a complete UI5 Web Components version upgrade in the ui5-webcomponents-react monorepo. Updates root and peer dependencies, regenerates wrapper components, syncs theming parameters, updates version-info, detects new components and breaking changes, and verifies the build. Use when a new @ui5/webcomponents version…
openagentskill-registry
Discover, compare, audit, and safely install reusable AI Agent Skills with OpenAgentSkill. Use whenever an agent needs a capability it does not already have, must compare Skill alternatives, or needs evidence before installing third-party instructions.
cli-commands
MUST use when using the CLI, including debugging job failures and inspecting run history via wmill job.
write-script-bun
MUST use when writing TypeScript scripts. Bun is the default and preferred TypeScript runtime — pick it for TypeScript unless the script specifically needs Deno.
write-script-python3
MUST use when writing Python scripts.
raw-app
MUST use when creating raw apps.