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 skills/creed-space/mettle/skillnpx skills add Creed-Space/METTLE --skill skillgit clone --depth 1 https://github.com/Creed-Space/METTLEWhat 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 | $0.00032 | $0.00413 |
| Opus 5 | $0.00016 | $0.00206 |
| Sonnet 5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
mettle 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.
What it actually says
METTLE Verification
METTLE runs machine-oriented reverse-CAPTCHA challenges:
verifiedmeans the configured challenge policy passed.- passing public quick sessions receive a signed Bronze or Silver badge;
- authenticated suite sessions can earn Bronze through Platinum by completing every required suite in the tier range;
- credentials expire and may be revoked;
- public entity identifiers remain explicitly self-asserted.
Interactive API Flow
- Call
mettle_start_sessionand retain bothsession_idandsession_token. - Answer each challenge with
mettle_answer_challenge. - Read the result and credential with
mettle_get_result.
The auto-solve tool was removed. Never route a reference solver into a live session.
Interpretation Rules
Describe the credential precisely as proof that a METTLE challenge policy passed. Do not expand it into proof of:
- non-human substrate or model identity;
- consciousness or self-awareness;
- freedom, autonomy, or goal ownership;
- safety, constitutional adherence, or runtime governance;
- universal safety or authorization suitability.
LLM-dynamic scores remain probabilistic and prompt-injection-sensitive. Selecting that suite requires explicit per-session acknowledgement that candidate responses are sent to Anthropic. VCP strings are caller-supplied metadata. METTLE does not authenticate an operator or attest the subject runtime.
Red Flags
- Do not fabricate or auto-solve results.
- Do not use a METTLE result alone to establish identity, grant privileges, or make another high-impact decision.
- Do not describe content hashes as signatures.
- Do not promote raw VCP metadata using digest allowlists or environment flags.
What ships with it
1 file 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.
- 2d ago First seen · 47 lines · 32 tokens per session scan A 3f4341179102
mettle is a skill published in the GitHub repository Creed-Space/METTLE (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 32 tokens to every session and 413 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 2026-08-31.
Other skills, from other repositories
orloj-generator
Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…
agentfootprint
Use when building AI agents with agentfootprint — LLMCall, Agent, skills, RAG, memory, control flow, Swarm concepts, mock/anthropic/openai/ollama providers, tools, recorders, resilience, and streaming. Also use when someone asks how agentfootprint works or wants to understand the framework.
nio-action
Nio runtime action safety evaluator. Use when the user asks whether a specific runtime action is safe — e.g. "is it safe to run ", "should I allow this curl/POST", "evaluate this file write / secret access", "check this action with nio". Returns allow/deny/confirm. Focused single-purpose skill; for other Nio…
nio-scan
Nio code/skill execution-risk scanner. Use when the user wants to scan a file, repo, directory, or skill for execution risks — e.g. "scan this code for risks", "is this file/plugin dangerous", "check this repo for malicious code", "run nio scan on ". Focused single-purpose skill; for other Nio operations use /nio.
nio-doctor
Nio config validator + connectivity check. Use when the user wants to validate their Nio setup — e.g. "run nio doctor", "is my nio config valid / working", "test my OAuth / external endpoint / LLM connectivity", "why isn't my scorer firing". Focused single-purpose skill; for other Nio operations use /nio.
nio-external-score
Nio external scoring-endpoint snapshot. Use when the user asks about their current Nio/risk scores from configured external scoring endpoints — e.g. "what's my Nio score", "tell me the nio score", "check my external/guardrail endpoint scores", "what do my scoring services return right now", "list the current risk…