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 skills/alexei-led/architect/tools-code-searchnpx skills add alexei-led/architect --skill tools-code-searchgit clone --depth 1 https://github.com/alexei-led/architectWhat 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 | $0.00117 | $0.01137 |
| Opus 5 | $0.00059 | $0.00568 |
| Sonnet 5 | $0.00023 | $0.00227 |
| Haiku 4.5 | $0.00012 | $0.00114 |
Grade A, and why
tools-code-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 2d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code search and targeted reading
Local search is the first evidence pass. It discovers where the architecture is implemented before heavier tools spend time proving graph or semantic facts.
Evidence dimensions: discovery and lightweight structural context.
When to use
Use during the system-map step and whenever a finding needs scoped file:line support before graph, AST, LSP, or language-tool confirmation. Good questions:
- Where are the entrypoints, deploy units, public interfaces, and package roots?
- Which files mention a domain concept, config key, route, queue, or dependency?
- Which modules import a boundary package or framework type?
- What docs, ADRs, manifests, or ownership files describe intended structure?
- Which exact files should the review read next?
This skill supports architecture-review; it does not assign architecture scores
or make findings by itself.
Commands
Run from the repo root. Prefer fd for paths and rg for text. Use the
runtime's file-read tool for targeted reads after search narrows the scope.
# High-signal structure and intent files
fd -H '(^README|CONTEXT|ARCHITECTURE|adr|decisions|ownership|CODEOWNERS|package.json|pyproject.toml|go.mod|Chart.yaml|kustomization.yaml|Dockerfile|\.github)' .
# Files by language / package marker
fd 'package.json|tsconfig.json|pyproject.toml|requirements.txt|go.mod|main.tf|Chart.yaml|kustomization.yaml'
# Exact concepts, routes, config keys, or dependency names
rg -n --hidden --glob '!{.git,node_modules,dist,build,vendor}/**' 'Order|Payment|Auth|Session|Repository|Controller|Handler|typeorm|sqlalchemy|kafka|redis'
# Import/dependency hints before AST or graph tools
rg -n --glob '!{.git,node_modules,dist,build,vendor}/**' "from ['\"]|import |require\(|package "
# Git-tracked scope, useful for generated/vendor exclusion
git ls-files
# Change hints when GitNexus is missing or stale
git log --name-only --pretty=format: -- <path> | sort | uniq -c | sort -nr | head
Prefer git grep -n <pattern> when the review should ignore untracked/generated
files and only search the versioned source. If the target is not a git repo,
record that limit and use scoped fd / rg instead.
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.
- 2d ago First seen · 110 lines · 117 tokens per session scan A 7a294d7dc9cb
tools-code-search is a skill published in the GitHub repository alexei-led/architect (2 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,137 once invoked, about $0.0006 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
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
map-wayfind
Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…
clipboard
Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
alphafold-database
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.