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.
npx agentmods add agents/adrielp/ai-engineering-harness/thoughts_locatorgit clone --depth 1 https://github.com/adrielp/ai-engineering-harnessWrote 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.
[](https://agentmods.dev/agents/adrielp/ai-engineering-harness/thoughts_locator)<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>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.
| Model | Per session | Once 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 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- thoughts-locator — 92% identical, 4 lines differ
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
-
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
-
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
-
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
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.
- 5d ago First seen · 95 lines · 43 tokens per session scan A 6b99ea7f34f9
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.
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.
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…
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.
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…
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.
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.