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 LichAmnesia/lich-skills --skill spec-driven-dev-v2git clone --depth 1 https://github.com/LichAmnesia/lich-skillsWrote 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/lichamnesia/lich-skills/spec-driven-dev-v2)<a href="https://agentmods.dev/skills/lichamnesia/lich-skills/spec-driven-dev-v2"><img src="https://agentmods.dev/badge/skills/lichamnesia/lich-skills/spec-driven-dev-v2/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/lichamnesia/lich-skills/spec-driven-dev-v2"><img src="https://agentmods.dev/badge/skills/lichamnesia/lich-skills/spec-driven-dev-v2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.03199 |
| Opus 5.5 | $0.00032 | $0.01280 |
| Sonnet 5.5 | $0.00016 | $0.00640 |
| Haiku 4.5 | $0.00008 | $0.00320 |
Grade A, and why
spec-driven-dev-v2 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Development v2
v1 assumed one agent shipping one feature in one session. v2 assumes an orchestrator (or a human) driving the agent across many sessions — possibly for days — and keeps work correct the entire time.
v2 adds:
- Three-layer hierarchy — Project → Sprint → Task
- Per-task state — JSON files an orchestrator can read to resume cold
- Review round-loop — review → feedback → modify → re-review until clean
- Worktree isolation — every task runs in a clean checkout, revertable alone
- Context pack — the briefing a reasoning-blind subagent reviewer needs
- Mechanical task gate — sizing/acceptance/rollback checks enforced by script
- Governance-as-code — boundary rules live in lint/CI, not markdown
- Artifact registry — new rules captured from reviews graduate to lint
When to use v2 over v1
Use v2 if any of:
- Expected agent time > 4 hours
- More than ~8 tasks, or more than one vertical slice
- A subagent (
/critic,Agent subagent_type=critic, etc.) reviews each task - An orchestrator (
/loop,autoresearch:ship,goal-driven) drives iteration - Architectural boundaries (layering, dependency direction) must hold mechanically
For one-session features, use spec-driven-dev (v1) — v2 is overhead for them.
The Hierarchy
context/
dev/
projects-001-<slug>/ # one project = one RFC
RFC.md # the contract: what & why
PLAN.md # sprint list + dependency graph
STATE.json # {current_sprint, status}
sprints-001-<slug>/ # one sprint = one checkpoint
SPRINT.md # goal, scope, exit criteria
TASKS.md # task status tracker
REVIEWS.md # review round log
STATE.json # {current_task, current_round, next_action}
tasks/
TK-001-<slug>.md # one task = one worktree
TK-002-<slug>.md
reviews/
RV-001-round1.md # round 1 for TK-001
RV-001-round2.md # after modify, round 2
RV-001-round3.md # …until verdict=approve
sprints-002-<slug>/
…
artifact-registry/
rules/
RULE-001-<slug>.md # captured pattern → lint rule
scripts/
governance-check.sh # boundary + state validator
task-lint.sh # mechanical task gate
What ships with it
12 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.
- scripts/governance-check.sh 6.6 KB runs code
- scripts/task-lint.sh 3.1 KB runs code
- templates/artifact-registry/RULE.md 2.4 KB
- templates/project/PLAN.md 2.8 KB
- templates/project/RFC.md 2.0 KB
- templates/project/STATE.json 319 B
- templates/review/REVIEW.md 4.9 KB
- templates/sprint/REVIEWS.md 1.4 KB
- templates/sprint/SPRINT.md 1.6 KB
- templates/sprint/STATE.json 550 B
- templates/sprint/TASKS.md 1.5 KB
- templates/task/TASK.md 2.2 KB
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 · 291 lines · 80 tokens per session scan A 562d27384583
spec-driven-dev-v2 is a skill published in the GitHub repository LichAmnesia/lich-skills (231 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 3,199 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
tendem-tasks
Use when a task is non-trivial and could benefit from human involvement — delegating work to a human expert (research, review, labeling, content, design, data work) and driving it end to end. Also use whenever Tendem is mentioned or its tools are in play.
tendem-task
Explicitly submit a new task to Tendem (hybrid AI + human experts) and drive it through scoping. Invoke as $tendem-task .
tendem-status
Explicitly check on a Tendem task and advance it (poll cleanly, don't busy-loop). Invoke as $tendem-status [taskid] — omit the taskid to pick from recent tasks.
parallel-execution-engine
Use when latency matters and several independent tasks can run at once -- a bounded implementation or investigation that needs waves of concurrent workers, not a persistent completion loop or stage-based orchestration.
subagent-team-orchestration
Use when a task is too large or too mixed for one agent -- it splits into research, planning, implementation, review, and verification stages, needs different specialties, or has parallelizable branches that still share dependencies.
handoff-discipline
Use when ending a session, handing a task back to the user, or approaching the context limit with work unfinished -- the next session or engineer must be able to resume the work instantly.