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 johnfkoo951/cmdspace-plugins --skill deepsearchgit clone --depth 1 https://github.com/johnfkoo951/cmdspace-pluginsWrote 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/johnfkoo951/cmdspace-plugins/deepsearch)<a href="https://agentmods.dev/skills/johnfkoo951/cmdspace-plugins/deepsearch"><img src="https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/deepsearch/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/johnfkoo951/cmdspace-plugins/deepsearch"><img src="https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/deepsearch.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 | $0.00072 | $0.00631 |
| Opus 5.5 | $0.00029 | $0.00252 |
| Sonnet 5.5 | $0.00014 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
deepsearch 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Search — Multi-Strategy Code Search
Applies multiple search strategies to find code that simple text search misses.
Workflow
Step 1: Understand Search Intent
Use AskUserQuestion:
{
"questions": [
{
"question": "What are you looking for?",
"header": "Search Type",
"options": [
{"label": "Pattern/Usage", "description": "Find all places where a pattern is used (e.g., all async functions, all API calls)"},
{"label": "Concept/Feature", "description": "Find code related to a concept (e.g., 'authentication', 'caching')"},
{"label": "Changed code", "description": "Find code that was recently modified or relates to a specific change"},
{"label": "Dead code", "description": "Find unused functions, imports, or variables"}
],
"multiSelect": false
}
]
}
Step 2: Apply Search Strategies
Dispatch explorer (Haiku) with instructions to apply multiple strategies in parallel:
Strategy 1: Textual Search
- Use Grep with regex patterns
- Search for exact names, patterns, and keywords
Strategy 2: Structural Search
- Use Glob for file pattern matching
- Trace import/export chains
- Follow function call hierarchies
Strategy 3: Semantic Search
- Search by concept (related terms, synonyms)
- Look in comments, docstrings, variable names
- Search for patterns that implement the concept
Strategy 4: Historical Search (if applicable)
- Use
git log --all -S "term"for code that appeared/disappeared - Use
git log --followfor file history - Use
git blamefor authorship and timing
Step 3: Rank and Present Results
## Search Results: [Query]
### Strategy Results Summary
| Strategy | Matches | Top Result |
|----------|---------|------------|
| Textual | [N] | [file:line] |
| Structural | [N] | [file:line] |
| Semantic | [N] | [file:line] |
| Historical | [N] | [commit] |
### Top Results (by relevance)
1. **[file:line]** — [context snippet]
- Found by: [strategy]
- Relevance: [why this matches]
2. **[file:line]** — [context snippet]
...
### Related Files
- [Files that are connected to the search results]
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.
- 1mo ago First seen · 85 lines · 72 tokens per session scan A 61badf32bda2
deepsearch is a skill published in the GitHub repository johnfkoo951/cmdspace-plugins (7 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 631 once invoked, about $0.0003 per session on Opus 5.5. 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
gh-issue-triage
An automated workflow for handling issues in a project's GitHub repository, from collecting and analysing them through fixing, testing, and closing them.
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
pr-reply
Answer reviewers on your own pull requests in other people's repos: find threads where the ball is on your side, tell humans from bots, do exactly what was asked and reply with evidence. Use at the start of any GitHub session or on a new-review alert. Triggers: /pr-reply, /prr, answer the reviewers, who is waiting on…
contrib-watch
Watch incoming feedback from outside engineers on your open-source repos: comments, reviews, issues, mentions. Use when you need to find who replied to your pull requests or issues, triage human versus bot responses, and answer within a day with evidence.
github-growth
A working guide for promoting projects and starting useful conversations on GitHub. GitHub is a platform for hosting code, reviewing changes, and discussing software with its users and maintainers.
share-fix
Turn a fix you made for a whole class of bugs into help for others: reverse-search GitHub for people hitting the same symptom, pick the 3-5 best live threads and post one tailored answer or gist each, no copy-paste fan-out. Use after a verified class fix. Triggers: /share-fix, /sf, share the fix.