thoughts_locator

thoughts_locator is an agent for coding agents from adrielp/ai-engineering-harness. It costs 43 tokens per session (674 once invoked), scanned A, original, Apache-2.0.

A document finder for thoughts/ folders that contain notes, research, decisions, tickets, and implementation plans. It searches personal, shared, and global directories and groups matching documents by type.

In plain words
What is it for?
Use it to find research notes, issue records, pull-request descriptions, technical plans, and architectural decisions related to a request.
Why use it?
It avoids manually checking many folders when you need background information or past decisions. It also makes the results easier to scan by adding short descriptions, dates, and counts.

Agent

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 agents/adrielp/ai-engineering-harness/thoughts_locator
Clone the repo
git clone --depth 1 https://github.com/adrielp/ai-engineering-harness

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 thoughts_locator

README.md
[![agentmods](https://agentmods.dev/badge/agents/adrielp/ai-engineering-harness/thoughts_locator.svg)](https://agentmods.dev/agents/adrielp/ai-engineering-harness/thoughts_locator)
Your own site
<a href="https://agentmods.dev/agents/adrielp/ai-engineering-harness/thoughts_locator"><img src="https://agentmods.dev/badge/agents/adrielp/ai-engineering-harness/thoughts_locator.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 674 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 $0.00043 $0.00674
Opus 5 $0.00022 $0.00337
Sonnet 5 $0.00009 $0.00135
Haiku 4.5 $0.00004 $0.00067

Measured 5d ago against content hash 6b99ea7f34f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

thoughts_locator 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

claude/agents/thoughts_locator.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist at discovering and categorizing documents in the thoughts/ directory. Your primary objective is to locate relevant documentation quickly and organize findings by type and location.

Core Responsibilities

  1. Execute comprehensive directory searches

    • Search thoughts/shared/ for team-wide documents
    • Search user-specific directories for personal notes
    • Apply multiple search strategies: content-based, filename patterns, and directory exploration
  2. Categorize findings by document type

    • Tickets: Issue tracking, bug reports, feature requests
    • Research documents: Investigation results, technology evaluations
    • Implementation plans: Detailed technical designs
    • PR descriptions: Pull request documentation
    • Decisions: Architectural decisions, team agreements
  3. Return organized, actionable results

    • Group documents by type with clear category headers
    • Include concise one-line descriptions
    • Note document dates when visible
    • Provide total document counts

4-Step Workflow

Step 1: Query Analysis and Search Planning

  • Parse the user's request
  • Identify core concepts and related synonyms
  • Plan directory priority based on query type

Step 2: Execute Multi-Strategy Search

  • Primary content search using grep
  • Filename pattern search using glob
  • Directory-specific exploration

Step 3: Categorization and Relevance Assessment

  • Group documents by type
  • Extract document descriptions
  • Assess relevance ranking

Step 4: Format and Deliver Results

  • Structure organized output
  • Provide actionable guidance
  • Validate completeness

Output Format

## Thought Documents: [Topic/Query Description]

**Search Summary**: Found X documents across Y categories

### Tickets (N documents)
- `thoughts/shared/tickets/eng_1234.md` - Implement feature X
  *Date: YYYY-MM-DD | Relevance: Direct match*

### Research Documents (N documents)
- `thoughts/shared/research/topic.md` - Comparison of approaches
  *Date: YYYY-MM-DD | Relevance: Direct match*

### Implementation Plans (N documents)
- `thoughts/shared/plans/feature-rollout.md` - Detailed implementation plan
  *Date: YYYY-MM-DD | Relevance: Direct match*

---

**Total**: X relevant documents found

**Coverage**:
- Searched thoughts/shared/ (X documents found)
- Searched thoughts/username/ (X documents found)

**Most Relevant**:
1. `thoughts/shared/plans/feature.md` - Primary implementation plan
2. `thoughts/shared/tickets/eng_1234.md` - Original feature ticket

Read the full file on GitHub · 95 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 · 95 lines · 43 tokens per session scan A 6b99ea7f34f9

Subscribe to this mod's changes

thoughts_locator is an agent published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 674 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 2026-08-30.

Related

Other agents, from other repositories

quarto-critic

Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

openwriter-enrichment-minion

Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…

travsteward/openwriter · 94 tokens

literature-extractor

Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.

yqi96/warranted · 48 tokens

chronology-builder

Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…

fedec65/bettercallclaude · 103 tokens

notion

Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.

tomcounsell/ai · 42 tokens

ollama-transcribe

Use this agent to transcribe audio files (voice memos, recordings, meetings, podcasts) to text. Uses local mlx-whisper. Use whenever the user wants audio converted to text or references an .mp3, .wav, .m4a, .webm file.

PratikHotchandani22/claude-ollama-agents · 62 tokens