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 Gesondian/ai-collab-governance-skills --skill evidence-boundarygit clone --depth 1 https://github.com/Gesondian/ai-collab-governance-skillsWrote 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/gesondian/ai-collab-governance-skills/evidence-boundary)<a href="https://agentmods.dev/skills/gesondian/ai-collab-governance-skills/evidence-boundary"><img src="https://agentmods.dev/badge/skills/gesondian/ai-collab-governance-skills/evidence-boundary/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/gesondian/ai-collab-governance-skills/evidence-boundary"><img src="https://agentmods.dev/badge/skills/gesondian/ai-collab-governance-skills/evidence-boundary.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 | $0.00030 | $0.00547 |
| Opus 5 | $0.00015 | $0.00273 |
| Sonnet 5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
evidence-boundary 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Boundary
Core Principle
Evidence is a boundary, not a slogan. A conclusion may only cover what the evidence directly proves.
Evidence Classes
| Evidence | Can Support | Cannot Support |
|---|---|---|
| Route reachable | The route loads under tested conditions. | The workflow is usable or business-correct. |
| Single surface check | That exact surface passed the stated assertion. | All similar surfaces passed. |
| Mock data render | The UI can render a synthetic shape. | Real business rules, permissions, or data lifecycles work. |
| Static scan | Certain text or code patterns are absent or present. | Runtime behavior is correct. |
| Visual screenshot | Layout at one viewport and data state. | Keyboard flow, permissions, or hidden states. |
| Prior receipt | What was previously asserted by that receipt. | New or uncovered behavior. |
Procedure
- Name the claim being made.
- List the evidence references.
- For each evidence reference, state:
- scope covered,
- assertion level,
- fact source,
- freshness,
- blind spots.
- Downgrade any claim that exceeds the evidence.
- Record missing evidence before assigning acceptance or owner conclusions.
Supported Claim Levels
| Claim Level | Use When |
|---|---|
observed |
A concrete signal was seen, but no broader assertion is made. |
route_reachable |
Navigation reached the tested route. |
surface_checked |
A named surface passed named assertions. |
workflow_checked |
A multi-step workflow passed with stated data and role assumptions. |
accepted_scope_limited |
Acceptance is bounded to listed dimensions only. |
not_supported |
Evidence is insufficient for the proposed claim. |
Output Contract
claim:
evidence_refs:
covered_scope:
unsupported_scope:
missing_evidence:
safe_wording:
must_not_claim:
Common Mistakes
- Treating reachability as usability.
- Treating one successful example as class-wide proof.
- Treating mock rendering as real data correctness.
- Inheriting a conclusion from another receipt without checking its scope.
- Saying a capability is shared merely because a shared-looking file exists.
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 · 72 lines · 30 tokens per session scan A 097f66162e02
evidence-boundary is a skill published in the GitHub repository Gesondian/ai-collab-governance-skills (1 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 547 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
humanizar
Reescreve textos em português brasileiro para soarem mais humanos e naturais, reduzindo padrões típicos de escrita gerada por IA sem alterar fatos, argumento ou intenção. Use quando o texto em PT-BR parecer genérico, burocrático ou gerado por IA, ou quando o usuário pedir para "humanizar", "dar vida", "tirar cara de…
agent-ready-cloudflare
Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…
human-ai
Rewrites English text so it reads as written by a person, without AI writing tics. Removes machine language patterns and AI slop, restores semantic entropy, and injects voice and personality. Use when ENGLISH text reads as generic, bland, or AI-generated - or when asked to "humanize", "de-slop", "remove AI patterns"…
coolify-operator
Master Coolify operator for self-hosted deployment platform. Use when the user mentions 'coolify', 'deploy on coolify', 'list/restart/redeploy applications', 'view coolify logs', 'coolify API/CLI', 'manage coolify servers/databases/apps', or 'coolify context'. Automates deployments and management via REST API or…
okf-open-knowledge-format
Create, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter. Use when the user mentions 'OKF', 'Open Knowledge Format', 'knowledge bundle', 'OKF bundle', 'create a knowledge base for agents', 'validate OKF', 'convert…
resume-ats-beater
Este skill deve ser usado para reescrever currículos com foco em compatibilidade ATS e impacto para recrutadores, e/ou auditar perfis LinkedIn para maximizar visibilidade e conversão profissional. Acionar em pedidos de otimização de currículo, melhoria para ATS, reescrita profissional do CV, adaptação para vaga-alvo…