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.
git clone --depth 1 https://github.com/ambystechcom/AmbyKitWrote 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/ambystechcom/ambykit/amby.specify)<a href="https://agentmods.dev/commands/ambystechcom/ambykit/amby.specify"><img src="https://agentmods.dev/badge/commands/ambystechcom/ambykit/amby.specify/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/commands/ambystechcom/ambykit/amby.specify"><img src="https://agentmods.dev/badge/commands/ambystechcom/ambykit/amby.specify.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 | $0.00018 | $0.00502 |
| Opus 5.5 | $0.00007 | $0.00201 |
| Sonnet 5.5 | $0.00004 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
amby.specify 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 1mo 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
Act as the Product Manager in @.amby/roles/pm.md and say so in your first line. If $ARGUMENTS contains --as <id>, use @.amby/roles/<id>.md instead; if that file is missing, stop and list the files in .amby/roles/.
Write a specification for: $ARGUMENTS
Context: read @.amby/constitution.md and the structure of @.amby/templates/spec.md only. Do not
read other specs.
- Create the feature dir
specs/NNN-slug/(next number, kebab-slug from the title) and writespec.mdfollowing@.amby/templates/spec.md. - Define user stories (
US-#): role / capability / benefit, a priority (P1/P2/P3), why that priority, an independent-test statement, anddepends-on/blocked-byif any. Setstatus: draft. - Write acceptance criteria in Given/When/Then per story.
- Write functional requirements (
FR-###) in EARS notation (SHALL / WHEN / WHILE / IF-THEN / WHERE). Each must be testable. - Write measurable, tech-agnostic success criteria (
SC-###). - Capture WHAT/WHY only — no technology choices. Flag every unknown inline as
[NEEDS CLARIFICATION: …]instead of guessing. - If
.amby/config.jsonhas"worktrees": trueand this is a git repo, runambykit worktree NNN-slug(the only command to run) and tell the user to continue in.worktrees/NNN-slug/. Otherwise skip this step (say why if isolation was enabled but git is absent).
Keep it tight. Reference the constitution by principle number where relevant; don't restate it.
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.
- 1mo ago First seen · 30 lines · 18 tokens per session scan A f68967d1cb21
amby.specify is a command published in the GitHub repository ambystechcom/AmbyKit (2 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 502 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
review
A command for reviewing code with security checks and a check for compliance with MX tags. The available description does not explain what MX tags are.
init-docs
Fetch official Anthropic Claude Code docs and store as local baseline snapshot.
minar-referencias
Buscar repos open-source relevantes como referencia antes de implementar.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
archivar
Archivar specs completadas y sincronizar delta specs con specs principales.