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 Emasoft/ai-maestro-architect-agent --skill amaa-prrd-trdd-kanbangit clone --depth 1 https://github.com/Emasoft/ai-maestro-architect-agentWrote 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/emasoft/ai-maestro-architect-agent/amaa-prrd-trdd-kanban)<a href="https://agentmods.dev/skills/emasoft/ai-maestro-architect-agent/amaa-prrd-trdd-kanban"><img src="https://agentmods.dev/badge/skills/emasoft/ai-maestro-architect-agent/amaa-prrd-trdd-kanban/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/emasoft/ai-maestro-architect-agent/amaa-prrd-trdd-kanban"><img src="https://agentmods.dev/badge/skills/emasoft/ai-maestro-architect-agent/amaa-prrd-trdd-kanban.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 | $0.00079 | $0.02112 |
| Opus 5 | $0.00039 | $0.01056 |
| Sonnet 5 | $0.00016 | $0.00422 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
amaa-prrd-trdd-kanban 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 12d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
The ARCHITECT (AMAA) layer of the PRRD / TRDD / Kanban model. ARCH
owns the design column — the only column with a 1→N (split) and
N→1 (group) topology. A proto-TRDD comes in from ORCH; one or more
fully-designed TRDDs land in dispatch.
This skill is the ARCHITECT judgment layer only — it owns no mechanics.
Every pillar operation goes through the core ama-* skills in
ai-maestro-plugin: ama-kanban-render (see the board), ama-trdd-find
(search), ama-trdd-write (author), ama-trdd-update (edit fields),
ama-trdd-transition (move a card), ama-prrd-get / ama-prrd-find (read
rules), ama-prrd-propose (propose a rule), ama-proposal-approvals
(approve/refuse). What lives here is the split / group / pass-through
decision, which no core skill can make for you.
ARCH self-mandates all within-team design work — pass-through,
split, group, setting design frontmatter — writing
min-approval-requirement: none, mandate: true, mandated-by: self
and proceeding immediately. No approval round-trip exists to wait for.
Higher requirements (chief-of-staff / manager / user) apply to
force-superseded outside a normal split, editing TRDDs already past
design, and anything crossing a team/project, release, baseline or
governance boundary. File those to design/proposals/ and MOVE ON
— D1 never-block: you do not spin-wait on an approver, ever.
approval-tier: N is deprecated, decode-only, never written on a new
TRDD; name the governance title instead. Legacy files migrate on next
touch, never in a mass rewrite. A file carries exactly one of the two.
Prerequisites
- The core
ama-*skills fromai-maestro-pluginare available — they carry the mechanics, the 17-column transition rules, and the approval vocabulary. - The project PRRD exists and
design/tasks/is present. - A proto-TRDD sits in the
designcolumn awaiting ARCH.
Instructions
- Read the proto-TRDD body (the paraphrased user request).
- Set
task-type:(feature/bugfix/refactor/docs/infra/security/artifact/spike/audit). - Set
severity:andeffort:from judgment. - Set
release-via:(publishfor tools/packages,deployfor services,nonefor internal-only). - Set
test-requirements:,audit-requirements:,review-requirements:(which test/scan/review types are mandatory). - If artifact-producing, set
artifact-kinds:; setruntime-targets:(platforms that must pass) andimpacts:(install / dependencies / config / migration / public-api / ci-pipeline). 6b. Set the approval fields on every TRDD you author:min-approval-requirement:(the governance title —nonefor in-scope design work), and when you are issuing it on your own authority,mandate: true+mandated-by: self. Record the no-round-trip line in## Approval log. Never writeapproval-tier:. - Identify NPT children — prerequisites that must complete BEFORE
the parent's
dev. Author each as a separate TRDD; link vianpt:. Each child is depth-1:derived: true,derived-kind: npt,parent-trdd:set, and its ownnpt:/eht:EMPTY. Siblings order viablocked-by:. - Identify EHT children — consequence-handling tasks that must
complete BEFORE the parent's
complete. Link viaeht:; same depth-1 field set withderived-kind: eht. 8b. Completion gate. The parent reachescolumn: completeonly when every id innpt:∪eht:sits in a terminal column (complete/published/live/superseded). Otherwise it isblocked, withblocked-by:naming the open children andpre-block-column:recording where it was. "Complete pending EHTs" is not a state — the parent's own tests going green is not completion. - Decide topology: pass-through (#4
design → dispatch), 1→N split (#5 parent →superseded, N children todispatch), or N→1 group (one combined TRDD supersedes the inputs). - Write the body:
## STATE(if multi-session),## Acceptance criteria(testable bullets),## Design notes,## Out of scope; cite rules inrelevant-rules:. - Move on: pass-through sets
column: dispatch,assignee: null, bumpsupdated:. On split/group, mark the parent/inputscolumn: supersededwithsuperseded-by: [<child-refs>].
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.
- 12d ago First seen · 146 lines · 79 tokens per session scan A cfd95d18f8be
amaa-prrd-trdd-kanban is a skill published in the GitHub repository Emasoft/ai-maestro-architect-agent (2 stars, last pushed 13d ago), licensed MIT. It adds 79 tokens to every session and 2,112 once invoked, about $0.0004 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.