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/plannpx skills add asimons81/hardproof --skill plangit 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 | $0.00023 | $0.00280 |
| Opus 5 | $0.00012 | $0.00140 |
| Sonnet 5 | $0.00005 | $0.00056 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
plan 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
Plan the Implementation
Purpose
Create an executable task sequence that preserves the approved design and makes progress inspectable.
When to use
Use for the PLAN stage selected by the active run context.
Inputs
Read the design, design approval, repository conventions, affected files, tests, migrations, documentation, and risk profile.
Procedure
- Decompose work into coherent tasks with observable outcomes.
- Name dependencies, likely files, risk, and acceptance checks.
- Include documentation and migration work with the behavior they describe.
- Add each task through
hardproof_task. - Record the complete plan through
hardproof_record.
Required records
Standard and Critical runs require a plan artifact, durable task records, and a separate human plan approval.
Exit criteria
Every required outcome maps to a task, dependencies are acyclic, and each task can be verified without relying on confidence.
Failure modes
Return to DESIGN if planning exposes a contract flaw. Do not create vague tasks, omit release work, or grant approval through a model tool.
Verification
Check task coverage and dependency order, then ask the human to use /hardproof approve plan. After approval exists, call hardproof_transition for IMPLEMENT.
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 · 35 lines · 23 tokens per session scan A 06e76242f06c
plan is a skill published in the GitHub repository asimons81/hardproof (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 23 tokens to every session and 280 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
repo-readiness-audit
Use when a user asks whether an identified repository is ready for further development, release work, a new feature, handoff, or a new contributor, requiring a disciplined read-only audit before an evidence-backed verdict.
dont-lie-to-me
Use when the user explicitly wants evidence-disciplined answers that separate observed facts, sourced claims, user reports, inference, unknowns, and contradictions before making strong factual or completion claims.
x-post-writer
Use when drafting, rewriting, or repurposing short-form X content, including single posts, quote posts, replies, threads, launches, and personal stories, with source fidelity and claim verification built in.
x-analytics-import
Use when X Analytics CSV exports must be inspected, validated, normalized, imported, or compared through a repeatable private-by-default workflow.
hermes-skill-consolidate
Use when installed Hermes skills must be safely consolidated, restructured, deprecated, split, or given shared references after overlap has been established, with a read-only plan, explicit approval, rollback snapshot, staged writes, and post-change verification.
hermes-environment-migration
Use when a Hermes environment must be safely migrated between machines with staged exports, integrity manifests, secret separation, selective imports, verification, and rollback.