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 agentmods add commands/dinhnguyenngoc/spec-driven-claude-code/plangit clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-codeWrote 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/commands/dinhnguyenngoc/spec-driven-claude-code/plan)<a href="https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/plan"><img src="https://agentmods.dev/badge/commands/dinhnguyenngoc/spec-driven-claude-code/plan.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 | $0.00014 | $0.05332 |
| Opus 5 | $0.00007 | $0.02666 |
| Sonnet 5 | $0.00003 | $0.01066 |
| Haiku 4.5 | $0.00001 | $0.00533 |
Grade A, and why
plan 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan — Planning & Task Breakdown
"Vertical slices, not horizontal layers."
Purpose
Transform a specification into an ordered list of small, verifiable tasks. Each task delivers end-to-end functionality.
Workspace Mode: if the session root declares
Mode: workspace→ resolve the target repo perCLAUDE.md§Workspace Mode before anything else; every path, probe, and gate below is relative to the target repo, and the workspace disk-check applies at the gate.
Prerequisites
Required:
- A specification exists (
specs/SPEC.mdfrom/spec), passed Gate 1 — headerStatusis Approved, not Draft - Architecture exists (
architecture/from/arch) — greenfield: Gate 2 passed; brownfield B1/B2: the Phase A baseline + this change's CONFORMANCE-GATE verdict (a one-question check — do not skip it for "small" changes; the verdict IS the cheap path). Includesarchitecture/api/openapi.yamlwhen the feature has an API surface. - Understanding of the codebase structure
Workflow
Phase 1: Analysis (Read-Only)
- Spec-readiness pre-check — confirm the spec passed Gate 1: the header
Statusis Approved, every scenario has a stable ID (@US-XXX-Snn) and a testable, observable AC. If the Status is still Draft, a scenario is missing an ID, has a vague/untestable AC, or a needed behaviour isn't in the spec at all → do not start decomposing it. - Read the spec — Understand objectives and acceptance criteria
- Survey the codebase — Identify relevant files, patterns, and integration points. (Brownfield: consume
/discoverartifacts as the index — see §Brownfield Mode — do not re-survey the tree.) - Review architecture (if exists) — Check ADRs, API contracts, diagrams
- Map dependencies — Which components depend on which?
- Write the §Impact Analysis — synthesize steps 2–5 into the
plans/plan.md§Impact Analysis section (structure in §required structure below): every change item → affected surface, each cell backed by evidence (docs/CODEBASE_MAP.mdendpoint/DB-object inventory ·architecture/diagrams/component.md·architecture/api/openapi.yaml· SPEC §Permission Matrix · the/archCONFORMANCE-GATE verdict). This is the visible output of Phase 1 — the analysis is not allowed to live only in the planner's head.
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 · 270 lines · 14 tokens per session scan A 587868f43008
plan is a command published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 5,332 once invoked, about $0.0001 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 commands, from other repositories
spec-kitty.analyze
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
my-own-prompt
Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.
kiro-spec-tasks
Command "kiro-spec-tasks" from gotalab/cc-sdd, covering implementation tasks generator, core task, execution steps, step 1: load context and step 2: generate implementation tasks.
assign
Turn a backlog item (ID-NNN) into a scoped goal draft and route it into the right WORKFLOW lane. Writes .claude/goals/, never executes.
specmanager-build
Build one phase of a SpecManager feature's plan via the builder subagent. Stops at the phase boundary; never advances.
orchestrate
Orchestrate a whole project (or slice) of GitHub issues into resolution-gated waves of Orca child worktrees — one autonomous worker per ticket — and babysit every PR through CI, the applicable-lens review, and third-party feedback until the human merges. Waves are resolution-gated — merged PRs, corroborated no-change…