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 gigsmart/haiku-method --skill haiku-reset-intentgit clone --depth 1 https://github.com/gigsmart/haiku-methodWrote 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/gigsmart/haiku-method/haiku-reset-intent)<a href="https://agentmods.dev/skills/gigsmart/haiku-method/haiku-reset-intent"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-reset-intent.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 | $0.00057 | $0.00544 |
| Opus 5 | $0.00028 | $0.00272 |
| Sonnet 5 | $0.00011 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
haiku-reset-intent 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 7d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reset Intent
Wipe an entire intent — every stage, every branch, every artifact — and prepare to recreate it from a clean slate. The intent's title and description are preserved so the user doesn't have to retype them.
When to use this skill
The intent's description was wrong, or the studio choice was wrong, or something foundational went off-track at the elaborate-or-earlier phase and the user wants to start over with the same title.
Not the right tool when:
- One specific stage produced output the user doesn't like — that's
/reset-stage. Other stages stay intact. - The user wants to keep the intent's work but rewind a hat sequence — that's a feedback revisit, not a reset.
- The intent is fine and the user just wants to discard mid-flight edits — that's
git reset/git restore, not a workflow reset.
How to drive it
- Call
haiku_intent_listto find the intent. If multiple are active, ask the user which one. - Call
haiku_intent_reset { intent: "<slug>" }. The tool confirms via the SPA picker, preserves the title and description, and returns instructions to recreate. - Follow the returned instructions to call
haiku_intent_createwith the preservedtitleanddescription. If the preserved title looks auto-truncated (ends in…or is a mid-sentence fragment), rewrite it as a crisp 3–8 word summary before calling — don't re-save a broken title.
What gets wiped
- Every
stages/<stage>/directory under the intent. - Every
haiku/<slug>/*git branch (stage branches and intent main). - Every artifact, feedback file, decision log, drift snapshot, and elaboration record under the intent dir.
- The intent's tracking row in any per-project state.
What stays
- The intent's preserved title and description (returned by the tool for the recreate call).
- Other intents in the project. This skill is scoped to a single intent.
- The repo's mainline branch and history.
After reset
The engine has nothing to tick on — haiku_run_next will report no active intent until haiku_intent_create runs. Recreate the intent immediately to keep the workflow alive.
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.
- 7d ago First seen · 41 lines · 57 tokens per session scan A 126d777f1920
haiku-reset-intent is a skill published in the GitHub repository gigsmart/haiku-method (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 544 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
mass-line
A method for collecting feedback and facts from multiple people or sources, turning them into a plan, and checking the plan with those affected.
workflows
A workflow guide for tasks that need several kinds of reasoning in sequence, such as research, finding the main conflict, choosing a small starting point, and planning sustained work.
concentrate-forces
A decision-making method for situations where several tasks compete for limited time, attention, computing power, or budget.
protracted-strategy
A long-term planning method for difficult work that cannot be completed quickly, divided into stages with steady progress over time.
redteam-mindset
Red-team operator discipline — the mindset corrections that separate offensive testing from defensive WAPT. Built from authorized red-team work where conservative defaults caused multiple findings to be missed and one to be incorrectly retracted. Use at the START of any red-team engagement and again whenever feeling…