Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/0fuk/openaccp/validator-openaccp)<a href="https://agentmods.dev/skills/0fuk/openaccp/validator-openaccp"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/validator-openaccp.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01601 |
| Opus 5 | $0.00024 | $0.00800 |
| Sonnet 5 | $0.00010 | $0.00320 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
validator-openaccp 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validator OpenACCP
Run:
python tools/openaccp_validate.py --artifact <path> --ruleset <ruleset> --strict
For cross-checks:
python tools/openaccp_validate.py --artifact task-card.json --ruleset task-card --source-pack source-pack.json --strict
python tools/openaccp_validate.py --artifact handoff.json --ruleset handoff --task-card task-card.json --strict
python tools/openaccp_validate.py --artifact primary-orchestrator.prompt.md --ruleset prompt-record --expect-prompt-id <prompt-id> --strict
python tools/openaccp_validate.py --artifact primary.short-launcher.md --ruleset launcher --prompt-record primary-orchestrator.prompt.md --expect-prompt-id <prompt-id> --strict
python tools/openaccp_validate.py --artifact response-with-launcher.md --ruleset launcher-output --strict
python tools/openaccp_validate.py --artifact status.md --ruleset formal-report --preferred-language <language> --strict
python tools/openaccp_validate.py --artifact frontier.prompt.md --ruleset frontier-contract --strict
python tools/openaccp_validate.py --artifact execution-boundary.json --ruleset execution-boundary --strict
python tools/openaccp_validate.py --artifact lane-registry.json --ruleset lane-registry --strict
python tools/openaccp_validate.py --artifact .openaccp/coordination/child-ledgers/<lane-id>.json --ruleset child-ledger --strict
python tools/openaccp_validate.py --artifact source-status-registry.json --ruleset source-status-registry --strict
python tools/openaccp_validate.py --artifact decision-registry.json --ruleset decision-registry --strict
python tools/openaccp_validate.py --artifact .openaccp/coordination/frontier-closures/<lane-id>.json --ruleset frontier-closure --strict
python tools/openaccp_validate.py --artifact CARDS.md --ruleset card-registry --strict
python tools/openaccp_validate.py --artifact current-manifest.json --ruleset current-manifest --source-pack source-pack.json --strict
python tools/openaccp_validate.py --artifact sequence-registry.json --ruleset sequence-registry --strict
python tools/openaccp_validate.py --artifact consume-result.json --ruleset consume-result --strict
# Only for final accepted Frontier return or Primary-ready packet consume:
python tools/openaccp_validate.py --artifact consume-result.json --ruleset consume-result --frontier-closure .openaccp/coordination/frontier-closures/<lane-id>.json --strict
python tools/openaccp_validate.py --artifact machine-summary.json --ruleset machine-summary --strict
python tools/openaccp_validate.py --artifact return-wake.json --ruleset return-wake --strict
Use frontier-contract before launching or reusing a Frontier prompt. It checks the B2 lane contract, openaccp-frontier-orchestration-contract.v1 JSON block, subagent-first dispatch, child ledger, branch return gate, worktree decision, human-readable reporting, and fallback-only child launcher rule.
Use execution-boundary during Primary startup before B2 Frontier dispatch. It records working directory, product repo status/path, Primary-inferred base branch, source roots, test entrypoints, worktree policy, inference evidence, ambiguity notes, writable/read-only/forbidden paths, side-effect level, data risk, unresolved owner inputs, and b2DispatchGate.
Use lane-registry for the active Primary/Frontier control plane. It records project complexity, Frontier dispatch mode, lane-count reason, lane ids, objectives, authority, assigned CARDs, execution boundary, child ledger, latest consume refs, return gate status, and per-lane b2DispatchGate.
Use child-ledger inside each Frontier lane. It records every worker/reviewer/discovery/validation child with Prompt ID, taskId, authority, effects, returnWake, dispatch status, handoff status, wake status, consume status, and remaining risk. Response ID and handoffId become required by lifecycle when a child returns or a handoff is present. B3 child authority is invalid.
Use return-wake when a Frontier, worker, reviewer, discovery, validation, or task-card-only child returns actionable evidence. It checks the openaccp-return-wake-owner.v1 packet, return owner, wake channel, idempotency key, artifact refs, validation status, owner action, and early-return safety.
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.
- 5d ago First seen · 67 lines · 48 tokens per session scan A 01fc3483435c
validator-openaccp is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 29d ago), licensed MIT. It adds 48 tokens to every session and 1,601 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
hive-mind-advanced
Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory.
handoff-mesh
Built-in communication layer for multi-agent setups. Full-mesh handoff folders (any agent can hand off to any other), an hourly watcher that surfaces open handoffs, weekly archive cleanup, and a completion-reporting loop so every handoff is handled AND verified. The durable 'brain' counterpart to real-time channels…
agent-teams
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
orchestrate
This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.
agent-orchestration
Agent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous agent loops, coordinating multiple agents, evaluating CrewAI/AutoGen/Swarm, or orchestrating complex multi-step scenarios.
silicon-steward
人类供奉调度官，把人类该提供之资源、反馈与执行动作压成清单与协议.