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/asimons81/hardproof/orchestratenpx skills add asimons81/hardproof --skill orchestrategit clone --depth 1 https://github.com/asimons81/hardproofWhat 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 | $0.00028 | $0.00336 |
| Opus 5 | $0.00014 | $0.00168 |
| Sonnet 5 | $0.00006 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
orchestrate 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
Orchestrate Hardproof
Purpose
Turn a rough software request into an inspectable result whose completion claim is backed by current evidence.
When to use
Use when starting, resuming, or coordinating the full active Hardproof protocol rather than performing one stage in isolation.
Inputs
Begin with hardproof_run status, the injected run context, profile, blockers, durable records, current workspace, and required stage skill.
Procedure
- Load the stage-specific
hardproof:*skill named by run context. - Keep state in Hardproof records rather than relying on conversation history.
- Match ceremony to Quick, Standard, or Critical policy without weakening verification.
- Use
hardproof_recordandhardproof_taskfor durable work products. - Request every stage change through
hardproof_transition; the service, not prose, decides whether gates pass. - Use human commands for protected approvals and waivers.
Required records
Maintain the artifacts, decisions, tasks, review, evidence, risks, approvals, completion report, and learning decision required by the selected profile.
Exit criteria
The run reaches COMPLETE only after every enforced gate passes against current durable state.
Failure modes
Pause on missing authority or unsafe boundaries. Return to the appropriate earlier stage when facts, design, code, review, or evidence change.
Verification
Inspect status and evidence with hardproof_report. Treat missing, failed, indeterminate, or stale evidence as incomplete.
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 · 36 lines · 28 tokens per session scan A af43c9d301d4
orchestrate is a skill published in the GitHub repository asimons81/hardproof (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 28 tokens to every session and 336 once invoked, about $0.0001 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
package-evaluator
Evaluates Claude Code package quality across 6 dimensions for all 7 package types, producing scored audit reports. Triggers on: "evaluate package", "audit agent quality", "score this hook", "package audit", "skill quality check". NOT for LLM prompts, use prompt-lab.
agent-builder
Build AI agents and automate Claude Code programmatically via the Claude Agent SDK and headless CLI mode. Covers Python SDK, claude -p, SDK MCP servers, hooks, sessions. Triggers on: "build an agent", "agent SDK", "headless mode", "automate Claude", "programmatic agent".
handoff
Produces and refreshes .docs/handoff.md, a 200-line session-continuity runbook for coding agents. Captures git state, working-tree changes, last validation commands, session decisions, blockers, resume checklist, references, and greenfield scaffolds. Triggers on: "update handoff", "session handoff", "refresh handoff"…
paper-to-skill
Converts research papers into executable skill packages via document conversion, critical analysis, and co-evolutionary refinement. Triggers on: "convert this paper to a skill", "paper-to-skill", "extract methodology from paper", "make a skill from this paper". NOT for literature review, use research-critique.
mcp-to-skill
Converts MCP servers into on-demand skills to cut context window usage, classifying each tool by replacement strategy and generating the skill package. Triggers on: "convert MCP", "MCP to skill", "reduce context size", "too many tools", "tool token bloat", "MCP migration".
concord-relay
Keep this Grok session reachable by other Concord agents while idle.