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-statuslinegit 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-statusline)<a href="https://agentmods.dev/skills/gigsmart/haiku-method/haiku-statusline"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-statusline/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-statusline"><img src="https://agentmods.dev/badge/skills/gigsmart/haiku-method/haiku-statusline.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 | $0.00036 | $0.00865 |
| Opus 5 | $0.00018 | $0.00432 |
| Sonnet 5 | $0.00007 | $0.00173 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade B, and why
haiku-statusline scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Run the install command from the project (or pass `--global` to wire `~/.claude/settings.json`): How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Status Line
H·AI·K·U ships a custom Claude Code status line that shows, at a glance, where the active intent is in its lifecycle:
⬢ admin-portal-reimagine · ⬢⬢⬢⬣⬡⬡ development ❯ execute · 7/12 units
⬢brand mark · then the intent slug- the stage pipeline:
⬢complete ·⬣active (phase-hued) ·⬡pending - the active stage, a flow mark (
❯running ·⊘gated), and the phase (color-coded: execute=cyan, fix-loop=orange, review/approve=yellow, gate=magenta, elaborate=grey) - a phase-appropriate aggregate: units done in execute, findings closed in fix-loop, units in review/approve/gate
When you're not on an active intent (no .haiku/, the intent is sealed, or you're outside a project), it transparently falls back to whatever status line you had before — it's purely additive.
Install
Run the install command from the project (or pass --global to wire ~/.claude/settings.json):
haiku statusline install
This points Claude Code's statusLine at haiku statusline and saves your existing status line as the fallback (in .haiku/statusline-fallback.json, or ~/.haiku/ for --global). The status line refreshes on the next prompt.
- Default (no flag): wires the project
.claude/settings.json. --global: wires the user-level~/.claude/settings.jsonso the haiku line shows in every project (and falls back to your original line outside intents).
Remove
haiku statusline uninstall
Restores the original status line you had before install (or removes the statusLine key entirely if you had none). Add --global if you installed globally.
Preview
To see the line for the current project without installing, feed the status-line payload to the render command:
echo "{\"workspace\":{\"current_dir\":\"$PWD\"}}" | haiku statusline
Set NO_COLOR=1 for a plain (no-ANSI) line; set HAIKU_STATUSLINE_DEBUG=1 to print on stderr why it rendered nothing (no .haiku/, sealed intent, etc.).
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 · 58 lines · 36 tokens per session scan B 5ddb973a2f09
haiku-statusline is a skill published in the GitHub repository gigsmart/haiku-method (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 865 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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) development methodology with multi-agent orchestration. Use when running a structured spec-to-code workflow or decomposing a feature through the SPARC phases.
p12a-contemplation-right-mindfulness
A mindfulness and reflection guide for building ongoing awareness and improving personal and team decision-making.
pishi
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.