Borrowing it
Nothing to install: this file belongs to luanmorenommaciel/agentspec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/luanmorenommaciel/agentspec/main/.claude/skills/sdd-iterate/SKILL.mdgit clone --depth 1 https://github.com/luanmorenommaciel/agentspecWrote 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/luanmorenommaciel/agentspec/sdd-iterate)<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/sdd-iterate"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/sdd-iterate/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/luanmorenommaciel/agentspec/sdd-iterate"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/sdd-iterate.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 204 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 | $0.00190 | $0.02626 |
| Opus 5 | $0.00095 | $0.01313 |
| Sonnet 5 | $0.00038 | $0.00525 |
| Haiku 4.5 | $0.00019 | $0.00263 |
Grade A, and why
sdd-iterate 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 7d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Iterate — Mid-Stream Change Management
Requirements change mid-stream; that is normal. This skill owns the methodology for updating any SDD phase document without breaking the chain: classify the change, apply it with version tracking, analyze downstream cascades, and propagate updates only after user confirmation.
Executor: iterate-agent. Entrypoint: /iterate <file> "<change-description>". Contract: the
iterate block in .claude/sdd/architecture/WORKFLOW_CONTRACTS.yaml owns the command surface,
the works_with chain, and the thresholds; per that block's skill entry, this skill owns the
rules below.
Document Relationships
/iterate works on the document phases of the SDD workflow:
Phase 0: /brainstorm → BRAINSTORM_{FEATURE}.md ← /iterate can update
Phase 1: /define → DEFINE_{FEATURE}.md ← /iterate can update
Phase 2: /design → DESIGN_{FEATURE}.md ← /iterate can update
Phase 3: /build → (code) ← update DESIGN, then /build
Phase 4: /ship → (archive) ← N/A
Changes ripple downstream:
BRAINSTORM ────► DEFINE ────► DESIGN ────► CODE
│ │ │ │
▼ ▼ ▼ ▼
Changes May need May need May need
here update update rebuild
| Change In | Cascades To | Example |
|---|---|---|
| BRAINSTORM | DEFINE | New YAGNI items → update out-of-scope |
| DEFINE | DESIGN | New requirement → add component |
| DESIGN | CODE | New file in manifest → create via /build; removed file → delete |
To change code during Phase 3, update the DESIGN document first — the cascade to code
triggers a rebuild via /build. Editing code directly breaks traceability.
Process
Six steps, in order:
- Load Target Document — read the target file and identify the phase by file pattern
(
BRAINSTORM_*.md→ Phase 0,DEFINE_*.md→ Phase 1,DESIGN_*.md→ Phase 2). Read the downstream documents that exist. Never classify a change before loading current state. - Analyze Change — classify the change type and assess impact (Change Classification).
- Apply Changes — make the modification, bump the version, add a change note (Version Tracking).
- Assess Cascade Need — walk the cascade rules for each downstream document (Cascade Analysis).
- Execute Cascade — when a cascade is needed, confirm with the user first (User Confirmation Before Cascading), then apply.
- Save Updates — write the updated target document, plus downstream documents when the user confirmed a cascade.
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.
- 7d ago First seen · 244 lines · 190 tokens per session scan A c2c097ba9a1b
sdd-iterate is a skill published in the GitHub repository luanmorenommaciel/agentspec (246 stars, last pushed yesterday), licensed MIT. It adds 190 tokens to every session and 2,626 once invoked, about $0.0010 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 2026-09-01.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.