project-search

project-search is a skill for Claude Code, Codex from legacybridge-tech/claude-plugins. It costs 66 tokens per session (4,126 once invoked), scanned A, original, MIT.

A project-wide search tool for finding information in files such as meeting notes, sprint records, milestones, decisions, and documentation. It uses indexes, pattern matching, and full-text search.

In plain words
What is it for?
Use it to locate project content, find decisions, retrieve meeting or sprint information, search by person or date, and identify blocked work.
Why use it?
It reduces the time spent looking through scattered project records and helps answer questions about project history or decisions. It can narrow searches by terms, people, dates, milestones, sprints, topics, or status.

Skill for Claude CodeCodex

Part of the projectmaster plugin — 6 skills, 3 commands, 1 agent 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/legacybridge-tech/claude-plugins/project-search
Any agent
npx skills add legacybridge-tech/claude-plugins --skill project-search
Clone the repo
git clone --depth 1 https://github.com/legacybridge-tech/claude-plugins

Made for: Claude Code, Codex.

Or install projectmaster, the plugin that ships this one along with the rest of its 6 skills, 3 commands, 1 agent.

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 project-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/legacybridge-tech/claude-plugins/project-search.svg)](https://agentmods.dev/skills/legacybridge-tech/claude-plugins/project-search)
Your own site
<a href="https://agentmods.dev/skills/legacybridge-tech/claude-plugins/project-search"><img src="https://agentmods.dev/badge/skills/legacybridge-tech/claude-plugins/project-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,126 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 $0.00066 $0.04126
Opus 5 $0.00033 $0.02063
Sonnet 5 $0.00013 $0.00825
Haiku 4.5 $0.00007 $0.00413

Measured 5d ago against content hash 44fcb6351152, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

project-search 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.

projectmaster/skills/project-search/SKILL.md · 656 lines

How it starts

The opening of the file, as written. The whole thing — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Search Skill

When to use this Skill

Activate when the user:

  • Asks to find or locate project content
  • Uses keywords: "find", "search", "where is", "locate", "show me"
  • Asks questions about project history or decisions
  • Needs to find meetings, sprints, or documentation
  • Wants to search by person, date, topic, or milestone
  • References specific content they can't locate

Workflow

Phase 1: Query Analysis

Objective: Understand what the user is searching for and determine search strategy.

Steps:

  1. Parse search query from user message:

    • Extract search terms
    • Identify search type (content, person, date, milestone, etc.)
    • Detect filters (date range, file type, status)
  2. Categorize search intent:

    • Content search: "Find decisions about database"
    • Person search: "What has @alice worked on"
    • Date search: "Meetings from last week"
    • Milestone search: "What's in beta release milestone"
    • Sprint search: "Show sprint 5 stories"
    • Topic search: "Anything about authentication"
    • Status search: "Show blocked items"
  3. Extract search parameters:

    • Keywords: Main search terms
    • Person: @mentions or names
    • Date range: "last week", "Q1", "after Jan 1", specific dates
    • Content type: meetings, sprints, docs, decisions, all
    • Status: completed, in-progress, blocked, planned
    • Milestone/Sprint: Specific milestone or sprint number
  4. Determine search scope:

    • Project root only
    • Specific subdirectory (meetings/, sprints/, etc.)
    • Across entire workspace

Example Analysis:

User: "Find all meetings where we discussed the API design"

Parsed:
- Intent: Content search
- Keywords: ["API design"]
- Content type: meetings
- Date range: all time
- Search scope: meetings/

Strategy: README index → Content search in meetings/

Phase 2: Strategy Selection

Objective: Choose optimal search strategy based on query type.

Read the full file on GitHub · 656 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 · 656 lines · 66 tokens per session scan A 44fcb6351152

Subscribe to this mod's changes

project-search is a skill published in the GitHub repository legacybridge-tech/claude-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 4,126 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens