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 ulises-jeremias/agent-toolkit --skill trdgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/trd)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/trd"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/trd/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/ulises-jeremias/agent-toolkit/trd"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/trd.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 | $0.00054 | $0.00654 |
| Opus 5.5 | $0.00022 | $0.00262 |
| Sonnet 5.5 | $0.00011 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
trd 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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TRD — Technical Requirements (WHAT)
Template: references/default-template.md — local reference, kept up to date with the standard structure.
Default guardrails (before any final content)
- Apply
output-handshake: confirm where the final TRD will live and that a human will review. - Then follow the steps below.
When to use
- A PRD is approved (or the task is technical-only) and the team needs design-level agreement before build.
- You need API/data contracts, component boundaries, and test strategy aligned to standards.
- A client doc hub with PRD/TRD cross-links requires matching document structure.
Instructions
- Open the TRD template (
references/default-template.md). Align sections: Scope, Architecture overview, Data model / API contracts, Technical decisions (link ADRs and spikes), Dependencies, Risks & constraints, Testing strategy, Implementation plan. - Map from PRD: user stories and AC from the PRD should appear as addressed in the TRD with clear technical response; if no PRD exists, state that explicitly and list assumptions.
- For ADRs that block or explain design, use
adrto structure the decision, then link the task or ADR in the forge per your engagement. - Delegate repo facts to
assistant(conventions, CI, existing patterns); cite sources. - For ticket updates, use the appropriate tool (
clickup-cli,jira-*, etc.); keep task comments short with links to the Doc (perworkflow-generic-project).
What not to do
- Do not dump the full external template into this skill; use
references/default-template.mdas the local canonical reference. - Do not skip risks and testing when the TRD is a handoff artifact.
References
output-handshake— destination and reviewreferences/default-template.md— local TRD templatereferences/example-unified-api.md— TRD example for a full API migration (see PRD link in that file)references/example-api-migration.md— detailed TRD example with phases, architecture, and testing strategyprd— when work starts from product requirementsspike— research findings used as design evidenceadr— decision records linked from the TRDdevelopment-workflow— validation and traceability expectationsincident— failure handling / incident implications when relevantworkflow-generic-project— delivery gates and traceabilityclickup-cli,jira-*— ticket / comment operations (per engagement)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 50 lines · 54 tokens per session scan A 0b8cafc07d70
trd is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 654 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
helius
Skill "helius" from helius-labs/core-ai, covering helius — build on solana, prerequisites, 1. helius mcp server, 2. mcp router surface and 3. api key.
review-api-compat
Use when the user asks for an API compatibility review, breaking change review, proto breaking change review, buf breaking review, OpenAPI compatibility check, gRPC backwards compatibility audit, "are these API changes breaking", "did we break the wire", contract evolution review, or backwards-compatibility audit on…
review-reliability
Use when the user asks for a reliability review, production readiness assessment, stability analysis, graceful shutdown audit, drain or rollout review, timeout review, timeout budget check, deadline propagation review, circuit breaker or bulkhead review, retry and backoff review, goroutine leak or resource leak…
review-code
Use when the user asks for a code review, architecture review, Go review, Go best practices review, protobuf review, proto or API design review, SOLID review, design pattern review, package design review, coupling or cohesion review, testability review, "review this code", "is this well designed", "is this idiomatic…
tray-status-pedido
API de Status de Pedido da Tray (recurso /orders/statuses). Cobre o CRUD completo do CATÁLOGO de status de pedido da loja: listar, consultar por ID, criar, atualizar e excluir tipos de status, definindo nome, descrição, cores hexadecimais (backgroundcolor/fontcolor) e o tipo de fluxo (type: open/closed/cancelled).…
tray-multicd
API de Multi-CD (Centros de Distribuição) da Tray. Cobre o CRUD de centros de distribuição (/multicd/distribution-centers: listar, consultar, criar, atualizar e excluir CDs) e a gestão de estoque distribuído por CD (/multicd/stock/detailed/product/:id, /multicd/stock/detailed/variant/:id e PUT…