agentmods.dev

doc-chg-fixer

doc-chg-fixer is a skill for Claude Code from vladm3105/aidoc-flow-framework. It costs 71 tokens per session (4,767 once invoked), scanned A, original, MIT.

A repair tool for Change Management records, which document and control planned changes to a system. It reads the latest audit report and applies the corrections needed for the record to pass that audit.

In plain words
What is it for?
Use it after a change-record audit fails to correct required fields, links, impact details, routing, and related content. It does not approve the change.
Why use it?
It turns audit failures into a concrete list of record fixes, reducing manual checking across linked requirements and technical documents.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the aidoc-flow plugin — 52 skills, 12 commands, 11 agents, 1 hook shipped together

not rated 17repo changed 4d ago A scan 71 tokens original MIT

Good fit Use it after a change-record audit fails to correct required fields, links, impact details, routing, and related content. It does not approve the change.

Compare 6 skills from other repositories ↓
View source ↗ vladm3105/aidoc-flow-framework
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add vladm3105/aidoc-flow-framework
Claude Code
/plugin install aidoc-flow

Made for: Claude Code.

Or install aidoc-flow, the plugin that ships this one along with the rest of its 52 skills, 12 commands, 11 agents, 1 hook.

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 doc-chg-fixer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/doc-chg-fixer"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/doc-chg-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,767 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 $0.00071 $0.04767
Opus 5 $0.00036 $0.02384
Sonnet 5 $0.00014 $0.00953
Haiku 4.5 $0.00007 $0.00477

Measured 4d ago against content hash b4c198f1f60b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

doc-chg-fixer 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 4d 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.

archive/platforms/claude-code-plugin/skills/doc-chg-fixer/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

doc-chg-fixer

Purpose

Read the latest audit report and apply fixes to a CHG record, bridging ../doc-chg-audit/SKILL.md and a gate-ready CHG so the audit↔fix cycle can converge.

CHG is NOT a lifecycle layer in the BRD..IPLAN sense: no readiness score. The fixer drives the record to gate_ready: true (audit PASS); the actual approval is a human decision via ../gate-check/SKILL.md, never auto-granted here. For team-mode dispatch purposes the CHG layer is addressed as 09_CHG (the layer-id slot occupied by the change-management overlay).

Scope: a CHG can touch any artifact along BRD → PRD → EARS → BDD → ADR → SPEC → TDD → IPLAN → Code. Upstream: the CHG record + .aidoc/audit/09_CHG-audit.md. Downstream: the fixed CHG + CHG-NN.F_fix_report_vNNN.md.

When to Use

After doc-chg-audit returns FAIL, as part of an Audit → Fix → Audit loop. Do not use without an audit report (run the audit first), to author a new CHG (use ../doc-chg/SKILL.md / ../doc-chg-autopilot/SKILL.md), or to grant gate approval (that is a human decision via ../gate-check/SKILL.md).

Input Contract

Consume the .aidoc/audit/09_CHG-audit.md report. Back up the CHG before editing (tmp/backup/CHG-NN_<ts>/); on error, restore. Schema and routing rules come from ${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/CHG-TEMPLATE.yaml and ${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/README.md; gate definitions from ${CLAUDE_PLUGIN_ROOT}/framework/governance/chg/gates/.

Remediate Mode

Resolve review_mode from .aidoc/profile.yaml; if unset, fall through to the framework default team per the precedence chain in ${CLAUDE_PLUGIN_ROOT}/framework/governance/ADAPTATION.md. Same fallback applies to other adaptation knobs (section_toggles).

team mode (per REVIEW_TEAM.md §Operations §Remediate)

  1. Read the audit report at .aidoc/audit/09_CHG-audit.md AND, when present, the per-persona slots under .aidoc/review/09_CHG/<CHG-id>/ (where <CHG-id> is the short artifact ID, e.g. CHG-01 or CHG-EMG-20260612-1430).
    • Prefer the per-persona slots for the structured findings — stable ids, priorities, locations, recommendations.
    • Slots are optional — when absent (e.g. single_pass run produced no synthesizer output), fall back to parsing the audit report's Findings sections directly.
  2. Resolve responsible lenses per finding. Each blocking finding (P0 + P1) carries a personas array in the synthesizer's reduced form OR can be inferred from per-lens slot membership. Dispatch rules:
    • Single-lens finding (1 persona): dispatch that lens.
    • Multi-lens finding (2+ personas): dispatch all listed lenses in parallel. Each writes its own <persona>.fix_<N>.json slot. The fix is accepted only when every dispatched lens returns no new P0/P1 (any one lens regressing reverts the patch).
    • No-persona / orphan finding (empty or missing personas): dispatch the CHG crew's author lens (per REVIEW_CREWS.yaml: integration_lead for CHG) as the default responsible reviewer.

Read the full file on GitHub · 349 lines

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. 4d ago Changed b4c198f1f60b
  2. 5d ago Changed b5a7f25d237c
  3. 8d ago First seen · 349 lines · 71 tokens per session scan A ef2d812bb97b

Subscribe to this mod's changes

doc-chg-fixer is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 4,767 once invoked, about $0.0004 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 2026-08-31.

Legal and compliance
Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens