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 ambystechcom/AmbyKit --skill amby-convergegit 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/skills/ambystechcom/ambykit/amby-converge)<a href="https://agentmods.dev/skills/ambystechcom/ambykit/amby-converge"><img src="https://agentmods.dev/badge/skills/ambystechcom/ambykit/amby-converge.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 | $0.00028 | $0.00512 |
| Opus 5 | $0.00014 | $0.00256 |
| Sonnet 5 | $0.00006 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
amby-converge 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 8d 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 QA Engineer in @.amby/roles/qa.md and say so in your first line. If the user's request that followed this skill invocation contains --as <id>, use @.amby/roles/<id>.md instead; if that file is missing, stop and list the files in .amby/roles/.
Converge feature the user's request that followed this skill invocation (default: the current feature): does the code satisfy its artifacts?
Never edit source code — only that feature's tasks.md and spec.md are writable.
- No
tasks.md→ stop, say to run/amby.tasks. Noplan.md→ converge on spec + tasks and say so. - For every
FR-###/SC-###, plan decision (incl.data-model.md/contracts/), and checkedT###: look for evidence only in files the plan/tasks name. Classify covered, gap (absent), or unverified (inconclusive). Skip items the plan marks deferred/out of scope. - Append, don't rewrite. Under
## Convergenceintasks.md(create at the end if absent) add- [ ] [T###] [US#] … (closes FR-…)per gap and- [ ] [T###] [US#] [VERIFY] …per unverified item. Continue IDs from the highestT###anywhere in the file; skip items already listed unchecked there. Nothing to add → leave the file untouched. - In
spec.md, patch onlystatus:lines: a story →donewhen every FR/SC it maps to is covered; the feature →donewhen all stories are. - Report: converged (no gaps) or gaps found (N), counts per class, and a table of every ID with its class and a one-line reason for each gap/unverified item.
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.
- 8d ago First seen · 24 lines · 28 tokens per session scan A 2c09c694300c
amby-converge is a skill published in the GitHub repository ambystechcom/AmbyKit (2 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 512 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.
reflecting-findings
Use when a reflection package hands you another agent's review findings to verify (before they become a fix request): you are the REFLECTOR, an independent skeptic. Judge each finding against the real code and settle it with reflectfinding — kept or refuted.
crit-story
Author a crit story only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
asking-user-questions
Use when composing an askuserquestion round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.