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 mnm-matin/captain-search --skill captain-search-cligit clone --depth 1 https://github.com/mnm-matin/captain-searchWrote 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/mnm-matin/captain-search/captain-search-cli)<a href="https://agentmods.dev/skills/mnm-matin/captain-search/captain-search-cli"><img src="https://agentmods.dev/badge/skills/mnm-matin/captain-search/captain-search-cli.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 | $0.00092 | $0.00765 |
| Opus 5 | $0.00046 | $0.00382 |
| Sonnet 5 | $0.00018 | $0.00153 |
| Haiku 4.5 | $0.00009 | $0.00076 |
Grade A, and why
captain-search-cli 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 7d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Captain Search CLI
Use this skill for direct terminal work with Captain Search.
Resolve the entrypoint
- If you are inside a checkout of this repository, prefer
uv run csearch .... - If the project virtualenv is already active and
csearchresolves,csearch ...is acceptable. - Outside the repo root, use
uv run --directory /path/to/captain-search csearch .... - Only use published-package entrypoints such as
uvx --from captain-search csearch ...oruv tool install captain-searchafter a public package release exists. - If the user wants the public-install path or asks why
uvx csearchis wrong, explain thatcsearchis a script exposed by thecaptain-searchpackage, so the correct one-off form isuvx --from captain-search csearch .... - If the user wants a reusable agent install from this checkout, use
uv run csearch skill install --scope user. After a public release exists, preferuvx --from captain-search csearch skill install.
Pick the workflow
- For first-run install, auth, smoke tests, or a recommended setup path, read
references/onboarding.md. - For exact command construction, formats, and subcommand rules, read
references/commands.md. - For provider trouble, empty results, or rate limits, run
uv run csearch doctorfrom the checkout before assuming a backend is broken.
Non-negotiable CLI rules
- Use the short subcommands:
web,code,fetch,doctor,skill,mcp,version. - Do not use legacy
search-web,search-code,fetch-webpage, orserveexamples. - Bare
csearchorcaptain-searchprints help and exits0. Usemcpexplicitly for server mode. - Use
web --allfor breadth. Do not use--provider multior--provider all. web,code, andfetchall support--format json.- Treat exit code
0as top-level success only. Provider-level warnings or partial failures can still appear in the output. - Keep install guidance honest: do not present
uv tool install captain-searchoruvx --from captain-search ...as currently available unless the package has actually been published.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 52 lines · 92 tokens per session scan A 94b3d35ff1e1
captain-search-cli is a skill published in the GitHub repository mnm-matin/captain-search (0 stars, last pushed 4mo ago), licensed MIT. It adds 92 tokens to every session and 765 once invoked, about $0.0005 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 2026-09-01.
Other skills, from other repositories
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
lc-curate-context
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…
gpt-image-gen
MUST read before generating images. Detailed prompt-crafting guide for gpt-image models, covering tool routing (native imagegeneration server tool vs the generateimage tool), prompt structure from subject to background, verbatim text rendering, anti-patterns, and the revisedprompt feedback loop for iteration.
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
cocosearch-review-pr
Use when reviewing a GitHub PR or GitLab MR by URL. Fetches diff and metadata via API, then uses CocoSearch for blast radius analysis, dependency impact, pattern consistency, and test coverage assessment. Read-only by default; optionally pushes findings back as inline PR/MR comments after your confirmation.
cocosearch-add-grammar
Use when adding a grammar handler for domain-specific file formats that share a base language extension (e.g., GitHub Actions within YAML). Guides through YamlGrammarBase inheritance, content validation, separator spec, metadata extraction, tests, and registration.