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 commands/klh/speedy-claude/buildgit clone --depth 1 https://github.com/klh/speedy-claudeWrote 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/commands/klh/speedy-claude/build)<a href="https://agentmods.dev/commands/klh/speedy-claude/build"><img src="https://agentmods.dev/badge/commands/klh/speedy-claude/build.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 | $0.00014 | $0.00241 |
| Opus 5 | $0.00007 | $0.00120 |
| Sonnet 5 | $0.00003 | $0.00048 |
| Haiku 4.5 | $0.00001 | $0.00024 |
Grade A, and why
build 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 today.
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.
This is a copy
100% identical to build — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Invoke the klh-systematic-debugging skill if anything breaks; use ast-grep for identifier-shaped changes and sd/ambr for mechanical ones.
Pick the next pending task from the plan. For each task:
- Read the task's acceptance criteria
- Load relevant context (existing code, patterns, types)
- Write a failing test for the expected behavior (RED)
- Implement the minimum code to pass the test (GREEN)
- Run the full test suite to check for regressions
- Run the build/typecheck to verify compilation (
npx tsc --noEmit/dotnet build) - Commit with a descriptive message (gitleaks scans staged content — rotate anything it flags)
- Mark the task complete and move to the next one
Cadence rules: verify every 3rd edit to the same file (run/build then, not after the 5th). More than 5 planned changes to one file = re-read once, single whole-file Write. Every edit is syntax-checked automatically post-write; fix reported errors before continuing.
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.
- today Changed a8df089e1d0f
- 4d ago First seen · 19 lines · 14 tokens per session scan A 93754af699d8
build is a command published in the GitHub repository klh/speedy-claude (11 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 241 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to build, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.