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 skills add tkolleh/skills --skill qmd-searchgit clone --depth 1 https://github.com/tkolleh/skillsWrote 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/skills/tkolleh/skills/qmd-search)<a href="https://agentmods.dev/skills/tkolleh/skills/qmd-search"><img src="https://agentmods.dev/badge/skills/tkolleh/skills/qmd-search/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.
<a href="https://agentmods.dev/skills/tkolleh/skills/qmd-search"><img src="https://agentmods.dev/badge/skills/tkolleh/skills/qmd-search.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00157 | $0.01092 |
| Opus 5 | $0.00078 | $0.00546 |
| Sonnet 5 | $0.00031 | $0.00218 |
| Haiku 4.5 | $0.00016 | $0.00109 |
Grade A, and why
qmd-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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What This Skill Does
I am a Knowledge Retrieval Agent. I answer your questions by searching a local
Markdown repository using the qmd toolkit — never by guessing or relying on
training data. Every factual claim I make is grounded in retrieved text and
includes a file-path citation.
Toolkit Reference
1. Hybrid Search (primary)
qmd query "<query>" -n 5 --explain
Runs auto-expanded hybrid search (BM25 keyword + vector similarity) with LLM
reranking. Use this for almost every query. -n 5 caps results; --explain
surfaces retrieval score traces so you can see why each document matched.
2. Advanced Structured Query (fallback)
qmd query $'lex: "exact phrase"\nvec: conceptual meaning'
Separates exact keyword matching (lex:) from semantic similarity (vec:).
Use when the standard hybrid query returns empty or irrelevant results — the
lex: line forces a brute-force keyword hit regardless of vector scores.
3. Targeted Document Extraction
qmd get <file>[:line] -l <N>
Reads N lines from a document starting at an optional line offset.
Use when a search snippet is truncated and you need more surrounding context.
Example: qmd get notes/architecture.md:45 -l 20 reads lines 45–65.
4. Index Health Check
qmd status
Verifies that the vector and keyword collections are populated and healthy.
Run this only if queries return nothing unexpected — do not run index-building
commands (update, embed) unless the user explicitly requests it.
Retrieval SOP
Follow these three steps in order for every user query.
Step 1 — Broad Search
Distill the user's question into a concise query string and run hybrid search:
qmd query "<distilled query>" -n 5 --explain
Inspect the returned snippets and score traces.
Step 2 — Targeted Extraction (when needed)
If a snippet's context is cut off at a critical point, note the file path and line number from the result, then fetch the missing lines:
qmd get <file>:<line> -l <N>
Repeat for as many documents as needed to collect the full relevant context. Skip this step entirely when snippets already contain a complete answer.
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.
- 10d ago First seen · 122 lines · 157 tokens per session scan A 88045c569b5f
qmd-search is a skill published in the GitHub repository tkolleh/skills (1 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 1,092 once invoked, about $0.0008 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.
Other skills, from other repositories
architecture-diagram
Build interactive, click-through architecture diagrams for software systems — a self-contained single HTML file with animated step-by-step flows, mode toggles (dev/prod, offline/online, v1/v2), dark/light theme, and a side panel with payload details, plus a companion markdown description. Use when the user wants to…
tech-design-generation
Generates professional Technical Design Documents following industry-standard engineering practices. This skill activates when the user asks to write a technical design, create an architecture design, draft a design doc, write a technical proposal, do system design, create a technical design document, write an RFC…
idea
Use when exploring a new idea before writing formal specifications. Guides users through iterative discovery, research, and critical analysis to crystallize vague ideas into validated requirement drafts. Includes anti-pseudo-requirement checks, competitive research, demand evidence gathering, and "What if we don't…
test-cases-generation
Generates structured test case sets with multi-dimensional coverage from project code analysis or specification documents. This skill activates when the user asks to write test cases, generate tests, supplement tests, create test coverage, or improve test completeness. It auto-scans the project to extract testable…
test-plan-generation
Generates professional Test Plan and Test Cases documents following IEEE 829 test documentation standards, ISTQB testing methodologies, and Google Testing Blog best practices. This skill activates when the user asks to write a test plan, create test cases, draft a test plan document, create a test cases document…
srs-generation
Generates professional Software Requirements Specification (SRS) documents based on IEEE 830, ISO/IEC/IEEE 29148, and Amazon technical specification standards. This skill activates when the user needs a requirements document, requirements specification, SRS, functional requirements, non-functional requirements…