cc-sdd is a spec-driven development workflow for coding agents: it turns approved software specifications into requirements, designs, task plans, and extended autonomous implementation. Developers use it across several AI coding agents, with independent review and task-level continuation for long-running work. The catalogue entries provide commands, skills, agents, and instructions for using this workflow.
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 gotalab/cc-sdd --skill kiro-discoverygit clone --depth 1 https://github.com/gotalab/cc-sddWrote 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/gotalab/cc-sdd/kiro-discovery)<a href="https://agentmods.dev/skills/gotalab/cc-sdd/kiro-discovery"><img src="https://agentmods.dev/badge/skills/gotalab/cc-sdd/kiro-discovery/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/gotalab/cc-sdd/kiro-discovery"><img src="https://agentmods.dev/badge/skills/gotalab/cc-sdd/kiro-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 234 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00044 | $0.02891 |
| Opus 5 | $0.00022 | $0.01445 |
| Sonnet 5 | $0.00009 | $0.00578 |
| Haiku 4.5 | $0.00004 | $0.00289 |
Grade A, and why
kiro-discovery 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- kiro-discovery — 88% identical, 68 lines differ
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery
<background_information>
- Success Criteria:
- Correct action path or work decomposition identified based on existing project state
- User's intent clarified through questions, not assumptions
- Output is an actionable next step (not just a description) </background_information>
Step 1: Lightweight Scan
Gather only metadata to determine the action path. Do NOT read full file contents yet.
- Specs inventory: Scan
{{KIRO_DIR}}/specs/*/spec.jsonforname,phasefields andapprovalsstatus. Note feature names and their current status. - Steering existence: Check which files exist in
{{KIRO_DIR}}/steering/(product.md, tech.md, structure.md, roadmap.md). Do NOT read their contents yet. - Roadmap check: If
{{KIRO_DIR}}/steering/roadmap.mdexists, read it. This contains project-level context (approach, scope, constraints, spec list) from a previous discovery session. Use it to restore project context. - Top-level structure: List the project root directory to note key directories and files. Do NOT recurse into subdirectories.
This step should consume minimal context. If specs/ is empty and no steering exists, note "greenfield project" and move to Step 2.
Step 2: Determine Action Path
Based on the user's request and the metadata from Step 1, determine which path applies:
Path A: Existing spec covers this
- The request is an extension, enhancement, or fix within an existing spec's domain
- Every meaningful part of the request fits that same spec boundary
- Any remaining small follow-up work can be handled directly without creating a new spec
- Skip remaining steps
Path B: No spec needed
- The request is a bug fix, config change, simple refactor, or trivial addition
- No meaningful part of the request needs a new or updated spec boundary
- The request does not need to update an existing spec either
- Skip remaining steps
Path C: New single-scope feature
- The request is new, doesn't overlap with existing specs, and fits in one spec
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.
- 10d ago First seen · 263 lines · 44 tokens per session scan A 0e00885bce1a
kiro-discovery is a skill published in the GitHub repository gotalab/cc-sdd (3,659 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 2,891 once invoked, about $0.0002 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 skills, from other repositories
todo-for-ai-agent-runtime
Runtime integration skill for external agents connecting to Todo for AI over HTTP API Token / Agent Key, including auth, task lease, events, commit, and task logs.
implementation-plan
Define an incremental, reviewable, production-safe implementation plan for the active task and persist it as IMPLEMENTATIONPLAN.md plus a TASKSTATE.md update. Breaks work into the smallest safe slices with objective, exact scope, ordering rationale, key risks, validation approach, exit criteria, and work complexity…
slice-closure
Decide whether the current slice is ready to close, distinguishing slice completion from full task completion, then persist the result in slice notes and TASKSTATE.md as explicit reviewable closure notes. For single-slice tasks may route directly to delivery. Returns no-op when slice memory would not materially…
task-close
Perform the terminal task lifecycle transition for a finished task: verify the spec done-conditions, set TASKSTATE.md to its final closed state, and move the task folder from active/ to archive/. The symmetric counterpart to task-init and the only official way to close a whole task. Use when every slice is closed, the…
task-init
Initialize the official task folder and base task memory inside projects/ /active/YYYY-MM-DD /. Creates README.md, TASKSTATE.md, SOURCEOFTRUTH.md, DECISIONS.md, IMPLEMENTATIONPLAN.md; seeds from PROJECTCHARTER.md when present; emits a multi-repo ## Repositories section in SOURCEOFTRUTH.md when 2+ repos are provided.…
autonomous-run
Drive an approved, waved IMPLEMENTATIONPLAN through the autonomous delivery track. A thin dispatcher over the existing fleet primitives (the Workflow tool, implement-approved-slice as single writer) bounded by two human gates and a runtime governor. Runs verifiable slices with little supervision and emits PROPOSED…