A governance skill for recording a project's starting assumptions in a versioned Seed document. Once published, that starting point is frozen, and changes require a new version.

Use it to create, validate, freeze, supersede, and attribute Seed documents before later design and requirements work.

It prevents teams from quietly rewriting the original requirements to make later work or audits appear consistent. It also records which AI agent and human made each change.

sdd-seed — Skill for Claude Code and Codex by vladm3105

Install

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.

Any agent

npx skills add vladm3105/aidoc-flow-framework --skill sdd-seed

Clone the repo

git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-seed/github.svg)](https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-seed)

Your own site

<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-seed"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-seed/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-seed"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-seed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 442 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00040	$0.00442
Opus 5.5	$0.00016	$0.00177
Sonnet 5.5	$0.00008	$0.00088
Haiku 4.5	$0.00004	$0.00044

Measured 19d ago against content hash f2fef78dea39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdd-seed 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 19d 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.

framework/skills/sdd-seed/SKILL.md · 40 lines

What it actually says

SDD Seed Author

Framework skill — routes to framework/governance/SEED_CONTRACT.md (three rules, AI-attribution GOV-021, seed gap review gate). Paths below use <skills-root> = this framework/skills/ directory. Upstream of everything: modules (sdd-module) decompose the seed; the BRD absorbs, rejects, or defers each seed claim.

1. Freeze the starting point

A published seed version is immutable: once the first BRD of a cycle is authored against seed vN, vN is historical input. A finding of the form "the seed says X, the chain does not" resolves in the BRD, never by amending the published version. When an assumption genuinely changes, ship a supersede — archive vN, author vN+1 clean, link supersedes — authorized by a CHG with a seed_scope supersede decision. New mid-cycle human input outside the standing seed arrives through <project>/chg/, which already has a gate.

2. Attribute every AI touch

Any document an AI agent creates or modifies in a versioned tier must carry document_control + metadata naming the agent, the supervising human, the authorizing CHG, and the change. Backfill is mandatory when the carrier is missing. Lifecycle entries carry author (and chg_ref for modules) — the machine-checked half (CHG-L015); carrier completeness stays with the reviewer lens.

3. Seal and hand off

Run the seed gap review gate before modules begin. Next: sdd-module, then sdd-brd. Seed-phase drafting before the first BRD is the sole change needing neither CHG nor IPLAN — everything after it rides a vehicle.

Changes

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.

19d ago First seen · 40 lines · 40 tokens per session scan A f2fef78dea39

Subscribe to this mod's changes

sdd-seed is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 442 once invoked, about $0.0002 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 2026-10-26.

Project management

sdd-seed next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sdd-seedvladm3105/aidoc-flow-framework	Skill	17	5d ago	MIT	A	40	Claude Code, Codex
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	80k	7d ago	MIT	A	200	Claude Code, Codex
next-cache-components-adoptionvercel/next.js	Skill	144k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex