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-change-modegit 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-change-mode)<a href="https://agentmods.dev/skills/gigsmart/haiku-method/haiku-change-mode"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-change-mode/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.
<a href="https://agentmods.dev/skills/gigsmart/haiku-method/haiku-change-mode"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-change-mode.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.00529 |
| Opus 5 | $0.00015 | $0.00264 |
| Sonnet 5 | $0.00006 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
haiku-change-mode 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 9d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Mode
Change the execution mode of an in-flight intent. Use when:
- The mode chosen at start no longer fits (e.g.
discreteis too heavy for a small change, orcontinuousis too autonomous for high-risk work). - A teammate picked up an intent and wants different review semantics than the original owner.
- An intent was created with the wrong mode and you need to correct it before too much state accumulates.
Process
-
Resolve the intent. If no slug is in scope (current branch isn't a
haiku/<slug>/...branch), ask which intent to change. Otherwise infer from the branch. -
Call
haiku_select_modewith the intent slug. The tool elicits a mode value from the user. It will automatically:- Hide
quickfrom the picker if the intent has already started a stage (you cannot enter or leavequickmid-flight — it's single-stage by definition). - Hide all options except the current mode if the intent is in
quickand has started (no transition out is allowed). - For non-quick destinations: write
modeto intent.md and setstagesto the studio's full stage list (idempotent — restoring the full list is safe even if it was already there).
- Hide
-
Drive forward. After the mode is picked, call
haiku_run_next { intent: "<slug>" }. The workflow engine continues from wherever the intent currently is — mode changes don't reset stage progress.
Constraints
- No
quicktransitions mid-flight. Quick mode is single-stage and chosen at intent creation only. Switching into quick would amputate the rest of the workflow; switching out would suddenly add stages the user never reviewed. The engine refuses both. - Cannot change mode pre-studio. If
studioisn't set yet, the intent hasn't reached mode selection — use/haiku:haiku-startto drive the initial elicitation chain instead of this skill.
Notes
- This skill never accepts a free-form mode value as an argument. Mode is engine-managed; the only way to set it is through
haiku_select_mode's elicitation. discrete-hybridis a derived mode, not directly selectable. The engine computes it fromcontinuous+ per-stage external gates.
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.
- 9d ago First seen · 34 lines · 30 tokens per session scan A 1fd780fccdaf
haiku-change-mode is a skill published in the GitHub repository gigsmart/haiku-method (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 529 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 2026-08-30.
Other skills, from other repositories
contradiction-analysis
A structured way to analyze difficult problems by identifying competing forces, finding the main conflict, and deciding which side or issue has the greatest effect.
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.
concentrate-forces
A decision-making method for situations where several tasks compete for limited time, attention, computing power, or budget.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
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…