refresh-catalog

refresh-catalog is a skill for Claude Code from glitchwerks/claude-wayfinder. It costs 75 tokens per session (1,029 once invoked), scanned B, original, MIT.

A procedure for manually rebuilding the dispatch catalog, the index used to match requests to agents and skills. It regenerates that index from skill sidecars and agent frontmatter, which is metadata attached to those files.

In plain words
What is it for?
Use it after changing trigger metadata, when diagnosing catalog errors or stale-catalog warnings, or when you need to overwrite the catalog with a clean rebuild.
Why use it?
It helps when the catalog is stale, missing changes, or has been edited incorrectly. It provides a forced refresh when automatic freshness checks do not detect a source-file update.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the claude-wayfinder plugin — 5 skills, 6 hooks shipped together

Good fit Use it after changing trigger metadata, when diagnosing catalog errors or stale-catalog warnings, or when you need to overwrite the catalog with a clean rebuild.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/glitchwerks/claude-wayfinder/refresh-catalog
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 glitchwerks/claude-wayfinder --skill refresh-catalog
Clone the repo
git clone --depth 1 https://github.com/glitchwerks/claude-wayfinder

Made for: Claude Code.

Or install claude-wayfinder, the plugin that ships this one along with the rest of its 5 skills, 6 hooks.

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 refresh-catalog

README.md
[![agentmods](https://agentmods.dev/badge/skills/glitchwerks/claude-wayfinder/refresh-catalog/github.svg)](https://agentmods.dev/skills/glitchwerks/claude-wayfinder/refresh-catalog)
Your own site
<a href="https://agentmods.dev/skills/glitchwerks/claude-wayfinder/refresh-catalog"><img src="https://agentmods.dev/badge/skills/glitchwerks/claude-wayfinder/refresh-catalog/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 refresh-catalog

Your own site · 80×15
<a href="https://agentmods.dev/skills/glitchwerks/claude-wayfinder/refresh-catalog"><img src="https://agentmods.dev/badge/skills/glitchwerks/claude-wayfinder/refresh-catalog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,029 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00075 $0.01029
Opus 5 $0.00037 $0.00515
Sonnet 5 $0.00015 $0.00206
Haiku 4.5 $0.00007 $0.00103

Measured 10d ago against content hash 3e9b7fde3488, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

refresh-catalog scanned grade B with 1 finding 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 10d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

--skills-dir ~/.claude/skills \
skills/refresh-catalog/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/refresh-catalog

Force a fresh regeneration of the dispatch catalog and report the results.

When to use this skill

The bundled refresh-catalog-on-stale.js hook (see Bundled hooks) automatically rebuilds the catalog when a source file (skill sidecar or agent frontmatter) is newer than the catalog itself. This skill exists for cases the mtime heuristic misses or when you want to force a rebuild for debugging:

  • A sidecar edit did not bump a watched path's mtime.
  • You edited the catalog directly and want to overwrite with a clean rebuild.
  • You are diagnosing a [CATALOG ERROR] or [CATALOG STALE] banner.

Step 1: Record the catalog mtime before regeneration

Read the mtime of the catalog before running the generator. The catalog path is resolved from $DISPATCH_CATALOG_PATH if set, otherwise the documented default ~/.claude/dispatch-catalog.json. If the file does not exist, note "catalog absent before run".

python -c "
import os, datetime
p = os.environ.get('DISPATCH_CATALOG_PATH') or os.path.expanduser('~/.claude/dispatch-catalog.json')
if os.path.exists(p):
    t = os.path.getmtime(p)
    print(datetime.datetime.fromtimestamp(t).isoformat(timespec='seconds'))
else:
    print('absent')
"

Step 2: Run the catalog generator

Invoke claude-wayfinder catalog build with the consumer's source directories. The default layout follows Claude Code's standard ~/.claude/ tree; adjust the flags if your project uses non-standard paths.

claude-wayfinder catalog build \
  --skills-dir ~/.claude/skills \
  --agents-dir ~/.claude/agents \
  --plugin-overrides-dir ~/.claude/triggers \
  --plugins-dir ~/.claude/plugins \
  --builtin-agents-dir ~/.claude/triggers/builtin \
  --out "${DISPATCH_CATALOG_PATH:-$HOME/.claude/dispatch-catalog.json}" \
  --log ~/.claude/dispatch-catalog-build.log

Capture both stdout and stderr. Record the exit code.

  • Exit 0 — clean generation.
  • Exit 1 — fatal error; the catalog may not have been written.
  • Exit 2 — degraded catalog; a partial file was written but one or more entries were excluded due to validation issues.

Read the full file on GitHub · 116 lines

Files

What ships with it

1 file 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. 10d ago First seen · 116 lines · 75 tokens per session scan B 3e9b7fde3488

Subscribe to this mod's changes

refresh-catalog is a skill published in the GitHub repository glitchwerks/claude-wayfinder (2 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 1,029 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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

content-strategy

Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…

rampstackco/claude-skills · 120 tokens

stakeholder-communication

Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…

rampstackco/claude-skills · 103 tokens

analytics-strategy

Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…

rampstackco/claude-skills · 126 tokens

incident-response

Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…

rampstackco/claude-skills · 117 tokens

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens

agb-begriff-vorformuliert-305

Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.

Klotzkette/claude-fuer-deutsches-recht · 68 tokens