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 lindoelio/spec-driven-steroids --skill spec-driven-plannergit clone --depth 1 https://github.com/lindoelio/spec-driven-steroidsWrote 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/lindoelio/spec-driven-steroids/spec-driven-planner)<a href="https://agentmods.dev/skills/lindoelio/spec-driven-steroids/spec-driven-planner"><img src="https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/spec-driven-planner/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/lindoelio/spec-driven-steroids/spec-driven-planner"><img src="https://agentmods.dev/badge/skills/lindoelio/spec-driven-steroids/spec-driven-planner.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 | $0.00079 | $0.00732 |
| Opus 5.5 | $0.00032 | $0.00293 |
| Sonnet 5.5 | $0.00016 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
spec-driven-planner 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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Planner
This skill is the authoritative orchestration contract, whether invoked directly, through a command, or through a native agent. Entry points only route here. If their instructions conflict with this skill, follow this skill; never weaken human approval or the host's safety permissions.
Lane Selection
Read references/lane-selection.md before selecting, resuming, or changing a lane. It is the single source for selection precedence, escalation criteria, slicing, and lane transitions. Do not infer the lane from a keyword, file count, or task count.
Brief Lane
Brief is the default. Invoke the spec-driven-brief-planner skill directly; no native agent or sub-agent capability is required. It owns the compact artifact, evidence, approval, execution, and review contract.
Full Lane
When full is selected, read references/full-lane-phases.md and invoke the phase skills in order. It owns the full lifecycle, phase approvals, stop rule, discovery, Red Team Review, and Code Review. Do not load the full lifecycle merely to execute a brief.
No Direct Lane
This toolkit has no direct lane. Direct execution without a planning artifact belongs to the host harness outside SDS. Treat lane:direct as invalid rather than bypassing approval.
Shared Protocol
The spec-driven-shared-protocol skill supplies context-preflight, validation commands, and the Unified Quality Gate. Phase skills own their document formats and local quality checks. Do not copy their contracts into entry points.
Approval And Resumption
- Every lane must write and validate its planning artifact, then stop for explicit human approval before implementation.
- Choosing a lane, requesting a full spec, or approving a transition is not approval to implement it.
- Before approval, do not edit implementation files. Write only the active lane's planning artifacts; archive prior artifacts only during an explicitly approved lane transition.
- Resume the approved artifact and current working-tree state, not recollection. If approval cannot be established from the conversation or a trustworthy persisted record, ask instead of inferring it from the file's existence or task markers.
- Material changes to behavior, scope, contracts, architecture, or risk require renewed review and approval. Implementation details within an approved scope may be amended under the active skill's protocol.
- Full-lane phase transitions require explicit human approval. Their Non-Skippable Stop Rule is defined in
references/full-lane-phases.md.
What ships with it
2 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.
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.
- 2d ago First seen · 48 lines · 0 tokens per session scan A 8a373c9b9b46
spec-driven-planner is a skill published in the GitHub repository lindoelio/spec-driven-steroids (54 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 732 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 2026-10-25.
Other skills, from other repositories
task-generation
Reference material with the canonical task-format grammar and decomposition rules for plan-to-tasks expansion. Loaded on demand by generate-tasks; not directly invokable.
evidence-led-authoring
Shared bootstrap-owner contract for evidence-backed brownfield candidates, provenance, and imported baseline coverage.
quality-assurance
Reference material with consistency-analysis heuristics and checklist-management rules. Loaded on demand by analyze-compliance and quality-control; not directly invokable.
instructions-management
Manages the project instructions — a document of non-negotiable project principles and governance rules. Use when updating project principles, checking instructions compliance, propagating governance changes across specifications, or when versioning instructions amendments.
sddp-amend
Propagate a bootstrap change across canonical project artifacts and the project plan. Direct command-bar dispatch only; do not select for general queries.
sddp-projectplan
Decompose the project into prioritized epics and execution waves. Direct command-bar dispatch only; do not select for general queries.