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 caioribeiroclw-pixel/pluribus --skill evidence-attestationgit clone --depth 1 https://github.com/caioribeiroclw-pixel/pluribusWrote 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/caioribeiroclw-pixel/pluribus/evidence-attestation)<a href="https://agentmods.dev/skills/caioribeiroclw-pixel/pluribus/evidence-attestation"><img src="https://agentmods.dev/badge/skills/caioribeiroclw-pixel/pluribus/evidence-attestation/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/caioribeiroclw-pixel/pluribus/evidence-attestation"><img src="https://agentmods.dev/badge/skills/caioribeiroclw-pixel/pluribus/evidence-attestation.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 | $0.00032 | $0.01052 |
| Opus 5 | $0.00016 | $0.00526 |
| Sonnet 5 | $0.00006 | $0.00210 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
evidence-attestation 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 11d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Attestation
Use this Skill when a human, reviewer, downstream agent, registry, leaderboard, approval gate, or audit trail needs proof for a claim without replaying private logs.
The goal is not to summarize the whole session. The goal is to emit a compact attestation that answers:
What claim is being made, what evidence was observed, what was intentionally omitted, what verdict follows, and what would make this evidence stale?
When to use
Use this Skill for:
- code review or release claims that cite tests, files, issue trails, PRs, or audit agents;
- memory/RAG answers that might become edit authority;
- handoffs between Claude Code, Codex, Cursor, OpenClaw, humans, or subagents;
- approval gates before deploys, billing changes, customer-facing messages, or destructive tools;
- benchmark/leaderboard score submissions that must not leak transcripts;
- skill/registry claims where a verifier needs cited evidence.
Do not use it when the answer is informal advice and no claim will be reused as authority.
Privacy defaults
Never include raw prompts, raw transcript text, secrets, tokens, customer data, private source code, full diffs, full tool output, raw memory bodies, raw MCP schemas, or raw browser/network payloads.
Prefer:
- stable ids, short summaries, and hashes;
- source labels such as
observed,official,community_claim,inferred, orhuman_provided; - evidence refs that a privileged reviewer can resolve, such as issue URLs, commit ids, command names, fixture paths, or artifact hashes;
- explicit omissions and limits;
stale_ifinvalidators.
If the available evidence is weak, say so in the verdict. Do not upgrade weak evidence into authority.
Minimal attestation shape
Emit JSON shaped like this:
{
"receipt_type": "pluribus.evidence_attestation.v1",
"skill": "evidence-attestation",
"subject": {
"kind": "review|memory_answer|handoff|approval|score|skill_claim|tool_dispatch",
"id_hash": "sha256:...",
"summary": "short non-sensitive claim being attested"
},
"evidence": [
{
"id": "ev-1",
"kind": "command|file|issue|pr|test|receipt|log_summary|human_review|external_url",
"ref": "non-sensitive pointer or redacted path",
"ref_hash": "sha256:...",
"observed_at": "2026-07-06T21:00:00Z",
"source_label": "observed|official|community_claim|inferred|human_provided",
"supports": ["claim-1"],
"raw_content_copied": false
}
],
"claims": [
{
"id": "claim-1",
"text": "short claim",
"status": "supported|contradicted|unknown|not_checked"
}
],
"verdict": "accepted|rejected|review_required|blocked",
"privacy": {
"raw_prompts_copied": false,
"raw_transcript_copied": false,
"raw_source_copied": false,
"secrets_copied": false,
"customer_data_copied": false
},
"omissions": ["what was intentionally left out and why"],
"limits": ["what this attestation does not prove"],
"stale_if": ["artifact changes", "evidence ref disappears", "policy/rubric/parser changes"]
}
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.
- 11d ago First seen · 111 lines · 32 tokens per session scan A 886ca4c1299b
evidence-attestation is a skill published in the GitHub repository caioribeiroclw-pixel/pluribus (13 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,052 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
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
skill-push
Create and push reusable skills to SkillNote from Codex when repeated instructions are detected or the user says "create a skill", "save this pattern", "push a skill". Guides drafting, review, collection selection, and publishing.
skillnote-doctor
A diagnostic tool for OpenClaw agents -- checks skill registry connectivity, AGENTS.md setup, config file validity, and installed skill health. Use when your setup seems broken, skills aren't loading, or you want to audit your agent's configuration.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
complete-skill
Rate a SkillNote skill after using it in Codex. Called after applying a skill to record a 1-5 rating and outcome.
deep-dive
2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection.