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 xbklairith/kisune --skill spec-driven-implementationgit clone --depth 1 https://github.com/xbklairith/kisuneWrote 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/xbklairith/kisune/spec-driven-implementation)<a href="https://agentmods.dev/skills/xbklairith/kisune/spec-driven-implementation"><img src="https://agentmods.dev/badge/skills/xbklairith/kisune/spec-driven-implementation/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/xbklairith/kisune/spec-driven-implementation"><img src="https://agentmods.dev/badge/skills/xbklairith/kisune/spec-driven-implementation.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 | $0.00046 | $0.02061 |
| Opus 5.5 | $0.00018 | $0.00824 |
| Sonnet 5.5 | $0.00009 | $0.00412 |
| Haiku 4.5 | $0.00005 | $0.00206 |
Grade A, and why
spec-driven-implementation 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Implementation Skill
Purpose
Execute the planning artifacts produced by spec-driven-planning. The skill auto-detects which mode the feature is in and runs the matching playbook:
- Quick mode (
plan.mdexists) — follow bite-sized steps, run verification commands, commit. No RED-GREEN-REFACTOR. Tests welcome but not mandated. - Full mode (
tasks.mdexists) — strict TDD per task: RED → GREEN → REFACTOR, traceability to REQ-### IDs, quality gates between tasks.
Activation Triggers
- User says "implement this feature", "let's code this", "execute the plan"
- User mentions "tasks", "TDD", or "execution"
- User uses
/dev-workflow:specwithtasksorexecute - Planning phase is complete
Mode Detection (DO THIS FIRST)
Before doing anything, find the active feature folder and detect mode:
1. ls docx/features/ → pick most recent or user-named feature
2. Inside docx/features/[NN-name]/, look for:
- plan.md only → QUICK MODE
- tasks.md only → FULL MODE
- tasks.md + plan.archived.md → FULL MODE (post-upgrade; archive is informational, ignored for routing)
- plan.md + tasks.md (no archive) → STOP AND ASK: ambiguous state.
Likely a hand-conversion in progress.
Ask user which file is authoritative.
Do NOT auto-pick — risk of clobbering.
- neither → ERROR: "No plan/spec found. Run /dev-workflow:spec first."
plan.archived.md is informational only and never affects mode detection — a clean post-upgrade state has tasks.md + plan.archived.md and routes to Full.
Announce the mode:
"Detected [Quick/Full] mode from
docx/features/[NN-name]/[plan.md|tasks.md]. Running [Quick/Full] execution."
Then run the matching section below.
Quick Mode Execution
Source: docx/features/[NN-name]/plan.md
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 Changed 431aaf0be24c
- 10d ago Changed · -167 lines 0ad9839b04e5
- 1mo ago First seen · 352 lines · 46 tokens per session scan A 3060183b9446
spec-driven-implementation is a skill published in the GitHub repository xbklairith/kisune (3 stars, last pushed 8d ago), licensed MIT. It adds 46 tokens to every session and 2,061 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 2026-08-31.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…