detecting-doc-bloat

detecting-doc-bloat is a skill for Claude Code, Codex from aj604/toolshed. It costs 87 tokens per session (3,259 once invoked), scanned A, original, MIT.

A read-only audit for documentation that is repetitive, too verbose, duplicated, or no longer useful. It records evidence for each suggested change in a structured report.

In plain words
What is it for?
Finding content to cut, condense, distill, merge, move, or retire in READMEs, runbooks, references, and other project documents.
Why use it?
It separates evidence-based findings from personal opinions and ensures that a human approves any document change before another skill applies it.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the doc-lifecycle plugin — 7 skills, 2 agents shipped together

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.

agentmods
npx agentmods add skills/aj604/toolshed/detecting-doc-bloat
Any agent
npx skills add aj604/toolshed --skill detecting-doc-bloat
Clone the repo
git clone --depth 1 https://github.com/aj604/toolshed

Made for: Claude Code, Codex.

Or install doc-lifecycle, the plugin that ships this one along with the rest of its 7 skills, 2 agents.

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 detecting-doc-bloat

README.md
[![agentmods](https://agentmods.dev/badge/skills/aj604/toolshed/detecting-doc-bloat.svg)](https://agentmods.dev/skills/aj604/toolshed/detecting-doc-bloat)
Your own site
<a href="https://agentmods.dev/skills/aj604/toolshed/detecting-doc-bloat"><img src="https://agentmods.dev/badge/skills/aj604/toolshed/detecting-doc-bloat.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,259 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00087 $0.03259
Opus 5 $0.00044 $0.01630
Sonnet 5 $0.00017 $0.00652
Haiku 4.5 $0.00009 $0.00326

Measured 4d ago against content hash 59ff16e4bcff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

detecting-doc-bloat 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/plan-chunks.py, scripts/validate-bloat-output.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/doc-lifecycle/skills/detecting-doc-bloat/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detecting Doc Bloat

Drift asks whether a doc is accurate; bloat asks whether it still earns its tokens. This skill is a thin router: the engine owns scope, segmentation, membership, and validation; per-need references carry the verdict rules; you supply judgment one bounded chunk at a time. Three non-negotiables:

  1. A verdict requires evidence. Every verdict names the quote, code line, or grep that proves the finding — never "feels redundant".
  2. The result is structured, not prose. Verdicts per output-contract.md, shape-checked at every seam and audited by the engine. Approval of a record's digest is the only bridge from a finding to a file change.
  3. Read-only — this skill never edits. A human approves digests; fixing-docs applies the approved subset.

Every engine command below is python3 -m doclifecycle … with the plugin's engine/ directory on PYTHONPATH (plugins/doc-lifecycle/engine/README.md covers both spellings).

Doc kinds (the planner hints these; override only with stated evidence)

  • living — claim-style docs tracking the repo (README, CLAUDE.md, runbooks, reference). Rules: references/verdict-lenses.md.
  • narrative — opens with growing-docs' > As of anchor (the file's first line, or the first line under the title), wherever the file sits. Own bar; never a planning artifact. Rules: verdict-lenses.md.
  • planning — designs/specs/plans describing an intended change. Rules: references/planning-artifacts.md.

A directory of ephemeral artifacts is not a fourth kind: it is one RETIRE-DOC verdict over an enumerable scope, whose members the engine expands from the index (output-contract.md). That replaced the legacy POLICY record and its policy_scope config — a config still declaring the key plans normally, and the planner says so.

The audit (run these steps, in order)

Every artifact this audit writes — the plan, the verdicts, the report — goes to ${TMPDIR:-/tmp}/, never the work tree: fixing-docs' applier confines a run to its approval set's paths, so an audit artifact sitting in the tree reads as an unaccounted change and the apply refuses (apply-working-tree-not-confined). The steps and the invocation templates below reuse that same destination; only the filename changes per artifact.

Read the full file on GitHub · 219 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 First seen · 219 lines · 87 tokens per session scan A 59ff16e4bcff

Subscribe to this mod's changes

detecting-doc-bloat is a skill published in the GitHub repository aj604/toolshed (2 stars, last pushed 29d ago), licensed MIT. It adds 87 tokens to every session and 3,259 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.

Related

Other skills, from other repositories

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

add-cloud-flow

Integrates Power Automate cloud flows into a Power Pages site. Lists available flows, suggests relevant ones based on intent, identifies scenarios and web roles, creates metadata files, and generates client-side code to call flows. Handles both new flow registration and adding already-registered flows to additional…

microsoft/power-platform-skills · 91 tokens

configure-env-variables

Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…

microsoft/power-platform-skills · 119 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

elixir-idioms

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.

oliver-kriska/claude-elixir-phoenix · 44 tokens

security

Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.

oliver-kriska/claude-elixir-phoenix · 47 tokens