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 FortiumPartners/ensemble --skill ensemble-refine-trdgit clone --depth 1 https://github.com/FortiumPartners/ensembleWrote 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/fortiumpartners/ensemble/ensemble-refine-trd)<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-refine-trd"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-refine-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/fortiumpartners/ensemble/ensemble-refine-trd"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-refine-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 | $0.00032 | $0.03134 |
| Opus 5 | $0.00016 | $0.01567 |
| Sonnet 5 | $0.00006 | $0.00627 |
| Haiku 4.5 | $0.00003 | $0.00313 |
Grade A, and why
ensemble-refine-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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ensemble-full-refine-trd — 91% identical, 184 lines differ
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensemble Command: /ensemble:refine-trd
This Codex skill mirrors the Ensemble slash command /ensemble:refine-trd.
Follow the workflow below, adapt to the current repository, and keep outputs structured.
Refine and enhance an existing Technical Requirements Document based on stakeholder feedback, additional research, or identified gaps. Updates TRD while maintaining version history, traceability, and Design Readiness scoring.
Workflow
Phase 1: TRD Review
1. Current TRD Analysis Review existing TRD content and extract structural metadata
- Read the TRD file from the path provided in $ARGUMENTS
- Parse frontmatter for Document ID (TRD-YYYY-NNN), Version, PRD reference, Design Readiness Score
- Count total tasks (TRD-NNN pattern), total test tasks (TRD-NNN-TEST), total hours estimated
- Build dependency graph from [depends: TRD-NNN] annotations
- Check if Acceptance Criteria Traceability matrix exists
- Note current version number for bumping later
- PR format detection: scan TRD for '### PR ' followed by a digit within the '## Master Task List' section (from '## Master Task List' heading to the next '##' heading or EOF). If found: set PR_FORMAT=true and log 'TRD format: PR-stack'. Else: set PR_FORMAT=false and log 'TRD format: legacy phase/sprint'.
- If PR_FORMAT=true: count PR boundary sections; for each ### PR N: heading check whether a Shippable State: line immediately follows it; record MISSING_SHIPPABLE[N] for any that don't; record INFRA_ONLY_SHIPPABLE[N] for any whose Shippable State text contains only infrastructure language (e.g., 'scaffolding', 'setup done', 'infrastructure complete') with no user-observable capability.
2. Synthesis After reviewing the TRD, generate a numbered list of findings — do NOT make any edits yet.
Scan the TRD for the following categories of issues:
- Implementation tasks missing a [satisfies REQ-NNN] annotation
- User-facing implementation tasks missing a paired TRD-NNN-TEST task
- Missing or incorrect "Validates PRD ACs:" fields (must reference real AC-NNN-M sub-IDs)
- [satisfies] annotations that reference non-existent PRD REQ-NNN IDs
- Unclear or underspecified implementation details
- Missing error handling or recovery mechanism descriptions
- Missing performance targets or non-functional requirements
- Architecture decisions that are not justified or explained
- Integration points or external dependencies that are not fully specified
- Tasks with hour estimates >= 8h that should be broken into smaller tasks
- Long dependency chains (3+ sequential [depends: TRD-NNN] hops) that create execution bottlenecks
- Circular dependencies between tasks
- Missing or incomplete Architecture Decision section (should include alternatives with justification)
- Missing or outdated Acceptance Criteria Traceability matrix
- Missing Design Readiness Gate scorecard in frontmatter
- Tasks missing hour estimates entirely
- Stale references to files, APIs, or components that no longer exist in the codebase
- "(PR_FORMAT=true only) PR sections missing Shippable State: annotation — list each ### PR N: heading that lacks an immediately-following Shippable State: line"
- "(PR_FORMAT=true only) PR sections whose Shippable State describes only infrastructure or scaffolding with no user-observable capability — these must be rewritten or the PR must be split to deliver visible value"
- "(PR_FORMAT=true only) Tasks in PR N that [depends: TRD-XXX] where TRD-XXX belongs to PR N+1 or later — forward dependency violates the shippability guarantee of PR N"
- "(PR_FORMAT=false only) TRD uses legacy ### Phase N: or ### Sprint N: headings — offer optional conversion to ### PR N: format with Shippable State annotations to enable implement-trd-beads PR-stack mode (present as a low-priority suggestion, not an error)"
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.
- 9d ago First seen · 218 lines · 32 tokens per session scan A 203d7dba587b
ensemble-refine-trd is a skill published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 3,134 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
context-recovery
Recovers project handoff context from local Codex, Claude Code, Gemini, CodeBuddy, and codexmate-derived sessions. Use when the user asks what happened in prior project/PR/branch/file/error work, needs a handoff brief, wants old decisions or validations recovered, or asks to summarize cross-session project activity…
dev
This skill should be used when the user asks to start, restart, keep alive, or inspect the local pikiclaw development service, including npm run dev, local debug bot startup, dashboard verification, and dev log checks.
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
bmad-quick-dev-new-preview
Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.
bmad-check-implementation-readiness
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".
bmad-create-story
Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]".