An offline verifier for signed evidence files and evidence packages. It checks supported hashes, digital signatures, and Merkle proofs with fixed verification programs rather than asking an AI model to judge them.

Use it to verify supported evidence events, signed runs, route profiles, or safe evidence-pack directories and report the verifier's exact state.

It provides a deterministic result while preserving the original file digest and stated limitations.

gspc-verify — Skill for Claude Code by CSOAI-ORG/councilof-ai

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/CSOAI-ORG/councilof-ai

agentmods

npx agentmods add skills/csoai-org/councilof-ai/gspc-verify

Made for: Claude Code.

Or install gspc, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/csoai-org/councilof-ai/gspc-verify/github.svg)](https://agentmods.dev/skills/csoai-org/councilof-ai/gspc-verify)

Your own site

<a href="https://agentmods.dev/skills/csoai-org/councilof-ai/gspc-verify"><img src="https://agentmods.dev/badge/skills/csoai-org/councilof-ai/gspc-verify/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/csoai-org/councilof-ai/gspc-verify"><img src="https://agentmods.dev/badge/skills/csoai-org/councilof-ai/gspc-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 917 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00095	$0.00917
Opus 5.5	$0.00038	$0.00367
Sonnet 5.5	$0.00019	$0.00183
Haiku 4.5	$0.00010	$0.00092

Measured 3d ago against content hash 78576404cce7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gspc-verify 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 3d 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.

distribution/plugin/skills/gspc-verify/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GSPC & OSAIA SAFE Portable Verification Procedure (`gspc-verify`)

Purpose and Scope

Given an existing CSOAI evidence artifact, identify the matching deterministic verification procedure, execute the supported offline checks via packages/evidence-fabric/portable_skill_verify.py, report the exact verifier state and reason, and preserve the original artifact digest and limits[].

Hard Rule: Never ask a language model to decide whether an Ed25519 signature, SHA-256 digest, or Merkle proof "looks valid." Always invoke the deterministic verifier and quote its returned verdict_state and artifact_sha256 verbatim.

Supported Artifact Kinds

OSAIA SAFE Evidence Pack Directory (csoai.safe-evidence-pack/0.1)
- Contains FREEZE.json, SHA256SUMS, records/, events/, render/.
- Checked via safe_pack_verify.py --offline --pack <DIR>.
Signed Evidence Batch (csoai.signed-run/0.1 + csoai.evidence-batch/0.1)
- Checked via verify.py <BATCH.json> <BATCH.signed.json> <EVENTS.jsonl> --did <DID.json>.
Standalone Evidence Event or Route Profile (csoai.evidence-event/0.1, csoai.route-evidence/0.1)
- Checked via verify.py --structure <RECORD.json|EVENTS.jsonl>.

Procedure

Run the deterministic portable skill verifier:

python3 packages/evidence-fabric/portable_skill_verify.py --artifact <PATH> [--did <DID.json>] [--signed <BATCH.signed.json>] [--events <EVENTS.jsonl>]

Preserved State Vocabulary

Batch / Signature Verdicts: VALID, INVALID, UNVERIFIABLE_KEY, UNCHECKABLE
SAFE Pack Readback Verdicts: SELF_CONSISTENT_UNAUTHENTICATED_KEY, INVALID, UNCHECKABLE
Structure-Only Verdicts: STRUCTURE_VALID, INVALID (always reports "signed": false)
Six Evidence Event States: CONSISTENT, DIVERGENT, PARTIAL, UNMEASURED, UNCHECKABLE, NOT_DISCRIMINATING

Permission Boundary Note (`allowed-tools`)

The Agent Skills allowed-tools frontmatter field is an experimental client declaration and not an execution grant. When running cross-client portability evaluations, pass --client-boundary-observation <STATE> (ENFORCED, PROMPTED_FOR_APPROVAL, REJECTED_ACTION, IGNORED_EXPERIMENTAL_DECLARATION, or UNMEASURED) to record how the host client treated the declared tool boundary.

Read the full file on GitHub · 55 lines

Changes

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.

3d ago First seen · 55 lines · 95 tokens per session scan A 78576404cce7

Subscribe to this mod's changes

gspc-verify is a skill published in the GitHub repository CSOAI-ORG/councilof-ai (3 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 917 once invoked, about $0.0004 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 2026-10-24.

Security ai-governance compliance mcp mcp-server model-context-protocol x402

gspc-verify

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

GSPC & OSAIA SAFE Portable Verification Procedure (`gspc-verify`)

Purpose and Scope

Supported Artifact Kinds

Procedure

Preserved State Vocabulary

Permission Boundary Note (`allowed-tools`)

What this file has done since we first saw it

Other skills, from other repositories

complyedge-eu-ai-act-check-and-cite

governance-setup

code-executor-mcp

memory-search-mcp

web-research-mcp

x402-payments

gspc-verify

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

GSPC & OSAIA SAFE Portable Verification Procedure (gspc-verify)

Purpose and Scope

Supported Artifact Kinds

Procedure

Preserved State Vocabulary

Permission Boundary Note (allowed-tools)

What this file has done since we first saw it

Other skills, from other repositories

complyedge-eu-ai-act-check-and-cite

governance-setup

code-executor-mcp

memory-search-mcp

web-research-mcp

x402-payments

GSPC & OSAIA SAFE Portable Verification Procedure (`gspc-verify`)

Permission Boundary Note (`allowed-tools`)