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-full-implement-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-full-implement-trd)<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-full-implement-trd"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-full-implement-trd.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 | $0.00065 | $0.01523 |
| Opus 5 | $0.00032 | $0.00762 |
| Sonnet 5 | $0.00013 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
ensemble-full-implement-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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ensemble:implement-trd
Mission: This command implements a complete Technical Requirements Document (TRD) using modern git-town feature branch workflow. It creates a feature branch and delegates to ensemble-orchestrator which routes to tech-lead-orchestrator for structured TDD-based development including planning, implementation, testing, and quality gates.
Phase 1: Prerequisites & Feature Branch Setup
Step 1: Git Town Verification
Check git-town installation and configuration using validation script
Actions:
- Execute validation script - bash packages/git/skills/git-town/scripts/validate-git-town.sh
- Handle exit codes - 0 (success), 1 (not installed), 2 (not configured), 3 (version mismatch), 4 (not git repo)
- If validation fails, escalate with specific error message
- Ensure clean working directory (git status)
Step 2: TRD Staleness Gate
Check TRD freshness before creating a feature branch. Skip if branch already exists (resume). Algorithm defined in packages/development/skills/staleness-gate/SKILL.md.
Actions:
- Derive TRD_PATH from $ARGUMENTS (the .md path argument).
- Derive TRD_SLUG from TRD_PATH filename (lowercase, replace non-alphanumeric with hyphens).
- Resume detection: run 'git branch --list feature/<TRD_SLUG>-sprint-1'. If this returns a branch name: IS_RESUME=true. If empty: IS_RESUME=false.
- Execute the TRD Staleness Gate per packages/development/skills/staleness-gate/SKILL.md using TRD_PATH and IS_RESUME.
- On HALT from skill: do not proceed. Implementation stops.
- On RETURN from skill: continue to step 3 (Feature Branch Creation).
Step 3: Feature Branch Creation
Create sprint-1 feature branch using git-town skill interview template
Actions:
- Load interview template from packages/git/skills/git-town/templates/interview-branch-creation.md
- Extract TRD slug from TRD filename (lowercase, hyphens replacing spaces/underscores)
- Read ENSEMBLE_USE_STACKED_PRS env var: STACKED_PRS=true only if its value equals 'true' (case-insensitive), else false (DEFAULT — single PR). Log: 'Stacked PRs: <enabled if STACKED_PRS else disabled (single PR)>'.
- Set CURRENT_SPRINT=1. If STACKED_PRS=true: set CURRENT_BRANCH=feature/-sprint-1. If STACKED_PRS=false: set CURRENT_BRANCH=feature/ (single branch for the whole TRD).
- Validate branch name against pattern - ^[a-z0-9-]+(/[a-z0-9-]+)*$
- Set base_branch to main (or current default branch)
- Execute - git town hack <CURRENT_BRANCH> (creates the first branch off the default branch; fallback - git switch -c <CURRENT_BRANCH>)
- Verify branch creation successful (check git branch output)
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.
- 4d ago First seen · 125 lines · 65 tokens per session scan A ebeaeb5c5c02
ensemble-full-implement-trd is a skill published in the GitHub repository FortiumPartners/ensemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,523 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
am-command-build
Implement the next task incrementally — build, test, verify, commit.
tdd
Discipline skill — TDD red-green-refactor cycle. Use when implementing any feature or bugfix, before writing implementation code.
tdd
Enforces red-green-refactor TDD cycle with atomic commits per phase. Used when implementing features, fixing bugs, or when tests should drive the design.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.