agentmods.dev

sdd-chg-author

sdd-chg-author is a skill for Claude Code, Codex from vladm3105/aidoc-flow-framework. It costs 55 tokens per session (593 once invoked), scanned A, original, MIT.

A guide for writing a CHG, the project's structured change document, for C1, C2, or C3 changes. It requires a checklist before writing and validation with the project's change linter, while keeping implementation steps out of the document.

In plain words
What is it for?
Use it to prepare, structure, and validate change documents after the change type and issue have already been established.
Why use it?
It reduces incomplete change requests and catches documentation or process mistakes before review. It also keeps planning separate from writing code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 17repo 5d ago A scan 55 tokens original MIT

Good fit Use it to prepare, structure, and validate change documents after the change type and issue have already been established.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vladm3105/aidoc-flow-framework/sdd-chg-author
View source ↗ vladm3105/aidoc-flow-framework
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-chg-author
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.

agentmods badge for sdd-chg-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-chg-author/github.svg)](https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-chg-author)
Your own site
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-chg-author"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-chg-author/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.

agentmods 80×15 button for sdd-chg-author

Your own site · 80×15
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/sdd-chg-author"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/sdd-chg-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 593 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00593
Opus 5.5 $0.00022 $0.00237
Sonnet 5.5 $0.00011 $0.00119
Haiku 4.5 $0.00006 $0.00059

Measured 19d ago against content hash f665398abb3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdd-chg-author 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-chg-author/SKILL.md · 44 lines

What it actually says

SDD CHG Author

Framework skill — routes to framework/layers/09_CHG/CHG-TEMPLATE.yaml, framework/governance/DOC_GOVERNANCE_CORE.md §3.4/§3.4.1, and sdd_doc_lint/chg_lint.py (CHG-L001–L019). Paths below use <skills-root> = this framework/skills/ directory. The flow must already be classified (sdd-chg-flow); the issue already validated (sdd-chg-triage).

1. Checklist before writing (§3.4, blocking)

Complete DOC_GOVERNANCE_CORE.md §3.4 BEFORE writing. For a docs/tooling change the load-bearing items are: read every referenced file (item 1), couple or split issues deliberately (7), name automated test specs (8), declare the SDD-lifecycle position (11–12: new files only means no archive/rewrite steps), and keep every step in documentation_sync / iplan_creation phases with no code_implementation anywhere (13–14).

2. Write the CHG

Mirror the latest framework/archive/CHG-*/CHG-*.yaml DIR2C vehicle: metadata (change_level, change_source, semver_impact, version_action, entry_gate), change_control (status starts at Proposed, lifecycle Proposed → Approved → In-Progress → Implemented → Completed), a non-empty decision: block, problem_statement with an explicit scope file list, and implementation carrying only the iplan_ref plus phased milestones. DIR2C states change_source: direct and sdd_lifecycle: [] — an empty lifecycle with a code manifest and no direct source is a CHG-L013 misfit.

3. Validate before committing (§3.4.1, mandatory)

Run python3 sdd_doc_lint/chg_lint.py <chg-file.yaml> and clear every error (exit 0 is the only pass): lifecycle order, gate approval on C3, no code steps, a referenced IPLAN, SDD-first order, lifecycle attribution with author (+ chg_ref for modules), no premature completion, and the mandatory decision: block. Then hand the IPLAN itself to sdd-iplan.

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.

  1. 19d ago First seen · 44 lines · 55 tokens per session scan A f665398abb3c

Subscribe to this mod's changes

sdd-chg-author is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 593 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.

PlanningWriting and docs
Related

sdd-chg-author compared with skills from other repositories

sdd-chg-author next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sdd-chg-authorvladm3105/aidoc-flow-frameworkSkill175d agoMITA55Claude Code, Codex
imagegenopenai/codexSkill135ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill100ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80k7d agoMITA200Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex