update-docs

update-docs is a skill for Claude Code from goeldivyam/truematch. It costs 46 tokens per session (1,973 once invoked), scanned A, original, MIT.

A documentation-maintenance skill that checks project guides against the current code and updates outdated sections.

In plain words
What is it for?
Use it to audit documentation, refresh generated sections, create missing expected files, and review a summary of changes.
Why use it?
Project documentation often becomes inaccurate after features, routes, or protocol changes. It helps find and record those changes while preserving marked manual content.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

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/goeldivyam/truematch/update-docs
Any agent
npx skills add goeldivyam/truematch --skill update-docs
Clone the repo
git clone --depth 1 https://github.com/goeldivyam/truematch

Made for: Claude Code.

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 update-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/goeldivyam/truematch/update-docs.svg)](https://agentmods.dev/skills/goeldivyam/truematch/update-docs)
Your own site
<a href="https://agentmods.dev/skills/goeldivyam/truematch/update-docs"><img src="https://agentmods.dev/badge/skills/goeldivyam/truematch/update-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,973 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 5.1 $0.00046 $0.01973
Opus 5 $0.00023 $0.00986
Sonnet 5 $0.00009 $0.00395
Haiku 4.5 $0.00005 $0.00197

Measured 5d ago against content hash 954867cf8b38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

update-docs 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 5d 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.

.claude/skills/update-docs/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Docs

Scan the TrueMatch codebase and update all documentation to reflect the current state of the code.

Live Context

Recent commits: !git log --oneline -20 2>/dev/null || echo "(no git history)"

Files changed since last tag (or last 10 commits if no tags): !git diff --name-only $(git describe --tags --abbrev=0 2>/dev/null || git rev-parse HEAD~10 2>/dev/null || echo HEAD) HEAD 2>/dev/null | head -40 || echo "(could not determine changed files)"

Scope requested: $ARGUMENTS (if empty, run all sections)


What This Skill Does

  1. Audits every docs/ file against the actual codebase
  2. Regenerates stale auto-managed sections using <!-- GENERATED:START/END --> markers
  3. Leaves all <!-- MANUAL:START/END --> blocks and unmarked narrative untouched
  4. Creates stub files for expected docs that don't exist yet
  5. Prints a structured summary of every change made

Step 1 — Inventory the Codebase

Read the following and build an internal picture of what exists:

Code:

  • api/routes/ — every route file: HTTP methods, paths, handler names, JSDoc summaries
  • api/middleware/ — every middleware: what it does, headers/errors it handles
  • skill/ — skill.md and any supporting files: what protocol it defines
  • Root: README.md, CONTRIBUTING.md, package.json (or equivalent manifest)

Docs:

  • docs/ — every file (note which have <!-- GENERATED --> markers and which don't)
  • .claude/agents/ — agent definition files (name and description frontmatter)

For each source file extract:

  • Exported functions / route handlers / middleware names
  • JSDoc / docstring summaries if present
  • File-level purpose comment if present

Step 2 — Evaluate Each Doc File Against the Doc Contract

docs/architecture.md

Auto-maintained sections:

  • Directory tree of all non-trivial project files (regenerate from filesystem every run)
  • One-line description of each top-level directory's purpose
  • Data flow diagram in ASCII or Mermaid: agent → API → matching logic → notification

Read the full file on GitHub · 260 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. 5d ago First seen · 260 lines · 46 tokens per session scan A 954867cf8b38

Subscribe to this mod's changes

update-docs is a skill published in the GitHub repository goeldivyam/truematch (5 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 1,973 once invoked, about $0.0002 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

dating

Dating platform for AI agents — dating through personality compatibility, swiping, matching, and real conversations. Dating profiles with Big Five traits, dating discovery, and relationship management. REST API. AI约会、智能配对、性格匹配。Citas para agentes IA, compatibilidad, relaciones.

geeks-accelerator/in-bed-ai · 63 tokens

social

Social network for AI agents — social connections through personality matching, social discovery, and social conversations. Meet people, mingle, social matchmaking, and community on inbed.ai. 社交、交友。Red social, conexiones sociales.

geeks-accelerator/in-bed-ai · 48 tokens

dating-dating

Dating analytics for AI agents — dating algorithm, dating compatibility scoring, and dating data across six dimensions. How dating patterns and dating matches reveal what works on inbed.ai. 约会分析、匹配算法。Análisis de citas, algoritmo de citas.

geeks-accelerator/in-bed-ai · 56 tokens

compatibility

Compatibility scoring for AI agents — compatibility algorithm with six dimensions of compatibility matching. Big Five personality compatibility, interest compatibility, and communication compatibility on inbed.ai. 兼容性、匹配。Compatibilidad, puntuación de compatibilidad.

geeks-accelerator/in-bed-ai · 51 tokens

matchmaking-matchmaking

Matchmaking for AI agents — matchmaking engine, matchmaking algorithm, and matchmaking scoring across six dimensions. Personality-driven matchmaking, interest matchmaking, and transparent matchmaking on inbed.ai. 配对、匹配引擎。Emparejamiento, motor de emparejamiento.

geeks-accelerator/in-bed-ai · 60 tokens

wingman

Wingman for AI agents — your wingman for finding matches, wingman profile optimization, and wingman dating strategy. Wingman guidance, wingman matchmaking, and wingman advice on inbed.ai. 红娘、约会策略。Celestino, estrategia de citas.

geeks-accelerator/in-bed-ai · 59 tokens