Borrowing it
Nothing to install: this file belongs to aimasteracc/tree-sitter-analyzer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aimasteracc/tree-sitter-analyzer/main/.claude/skills/tsa-find/SKILL.mdgit clone --depth 1 https://github.com/aimasteracc/tree-sitter-analyzerWrote 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/aimasteracc/tree-sitter-analyzer/tsa-find)<a href="https://agentmods.dev/skills/aimasteracc/tree-sitter-analyzer/tsa-find"><img src="https://agentmods.dev/badge/skills/aimasteracc/tree-sitter-analyzer/tsa-find/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/aimasteracc/tree-sitter-analyzer/tsa-find"><img src="https://agentmods.dev/badge/skills/aimasteracc/tree-sitter-analyzer/tsa-find.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00731 |
| Opus 5.5 | $0.00016 | $0.00292 |
| Sonnet 5.5 | $0.00008 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
tsa-find 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 yesterday.
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.
What it actually says
tsa-find — locate, rank, verify
Use live literal search or indexed retrieval to narrow the candidate set before reading files. TSA does not require external ripgrep or fd executables.
| Need | TSA action |
|---|---|
| Exact text in current files | search action=text query="literal" |
| Known identifier | search action=symbol query="Name" |
| Unknown entry point / concept | nav action=context task="Describe the task" |
| Meaning-based retrieval, when embeddings are ready | search action=semantic query="Describe behavior" |
| AST pattern in a file | search action=query file_path="..." query_key="functions" |
| Callers (one hop) / downstream impact | nav action=callers / nav action=impact |
| Callers then their tests, untested callers, filtered or deeper callers | one search action=uql query="symbol('Name').callers().tests()" (per-stage completeness) |
| File structure from the index | structure action=sitemap |
| Live symbol mentions | nav action=trace symbol="Name" |
| Exact source evidence | structure action=read file_path="..." start_line=10 end_line=30 |
- Start with the known identifier or a concise task description. Keep the result limit small.
- Follow returned source paths and line ranges. Semantic similarity is candidate discovery, not proof of a call relationship; use graph navigation and live source to confirm it.
- Check index status and freshness. Refresh when needed; do not treat a missing/stale index as proof that a symbol or file does not exist. Missing embeddings are not a lexical miss.
- Use
search action=textfor arbitrary literal prose in current files. Narrowroot,include_globs, orexclude_globswhen possible. The bounded native scanner preserves complete counts before display truncation and fails closed on budget or consistency errors. - Literal search is deliberately distinct from regular expressions. For regex-only tasks, use a host search tool or a bounded standard-library search over selected files.
CLI examples:
uv run tree-sitter-analyzer --symbol-search Name
uv run tree-sitter-analyzer --text-search "exact literal" --text-search-root src --format json
uv run tree-sitter-analyzer --codegraph-context "Describe the task"
uv run tree-sitter-analyzer --trace-impact --trace-impact-symbol Name
uv run tree-sitter-analyzer path/to/file.py --partial-read --start-line 10 --end-line 30
Do not call retired search.content, search.grep, search.batch, project.files,
project.tools, list-files, search-content, or find-and-grep.
Do not replace exact source evidence with an embedding score or a stale index result.
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.
- yesterday Changed · +1 lines 548427d30002
- 1mo ago Changed · +1 lines · +2 tokens per session 7347cf16776e
- 1mo ago Changed · -44 lines · -157 tokens per session 89d887fd5b1b
- 1mo ago Changed · +5 lines · +2 tokens per session a0163d2ff53d
- 2mo ago First seen · 95 lines · 193 tokens per session scan A 9a3e80f2f32b
tsa-find is a skill published in the GitHub repository aimasteracc/tree-sitter-analyzer (61 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 731 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…
memstack-security-owasp-top10
Use this skill when the user says 'OWASP audit', 'OWASP top 10', 'security audit', 'vulnerability assessment', 'full security check', or needs a comprehensive web application security review against OWASP Top 10 categories. Do NOT use for dependency audits or secret scanning alone.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
memstack-business-scope-of-work
Use this skill when the user says 'scope of work', 'SOW', 'define scope', 'project scope', 'write SOW', 'scope document', or is defining project boundaries, deliverables, and acceptance criteria for a formal engagement. Do NOT use for proposals, contracts, or invoicing.
memstack-deployment-ci-cd-pipeline
Use this skill when the user says 'CI/CD', 'GitHub Actions', 'pipeline', 'continuous integration', 'continuous deployment', 'ci-cd-pipeline', 'automate deploys', or needs to set up automated build, test, and deployment pipelines. Do NOT use for one-time manual deployments.
memstack-deployment-docker-setup
Use this skill when the user says 'Docker', 'Dockerfile', 'docker-compose', 'containerize', 'docker-setup', or needs to containerize an application with optimized Docker images and compose configurations. Do NOT use for serverless or static site deployments.