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 alexei-led/architect --skill tools-ast-grepgit clone --depth 1 https://github.com/alexei-led/architectWrote 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/alexei-led/architect/tools-ast-grep)<a href="https://agentmods.dev/skills/alexei-led/architect/tools-ast-grep"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/tools-ast-grep.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 | $0.00102 | $0.01031 |
| Opus 5 | $0.00051 | $0.00515 |
| Sonnet 5 | $0.00020 | $0.00206 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
tools-ast-grep 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ast-grep
ast-grep matches code by its syntax tree, so a pattern survives reformatting,
whitespace, and comments that defeat grep. It is the cheapest way to answer
"does this pattern exist where it shouldn't?" with a precise file:line list.
Evidence dimension: structural. Output is a concrete evidence ref per match.
When to use
Use when a finding hypothesis is a structural code pattern: "domain code imports the ORM directly," "routes are declared outside the router module," "this framework type leaks past the boundary," or "a module exports too much surface." ast-grep confirms presence/absence with line-anchored hits. Use it before claiming a boundary is bypassed — a claim about a pattern needs the matched lines.
Commands
Run from the repo root. -l sets language; -p is an inline pattern; --json
gives machine-readable hits for counting.
# Imports of a specific package (TS/JS)
ast-grep -l ts -p 'import $$$ from "typeorm"'
# Direct DB access leaking into a layer (scope with a path)
ast-grep -l ts -p 'createConnection($$$)' src/domain
# Exported symbols (surface-area survey)
ast-grep -l ts -p 'export $$$'
# Route declarations outside the router (framework leak)
ast-grep -l ts -p 'app.$METHOD($PATH, $$$)'
# Framework type used past the boundary (Python example)
ast-grep -l python -p 'Request' src/core
# Count hits without dumping every match
ast-grep -l go -p 'sql.Open($$$)' --json | jq length
For reusable, named rules (relational metavariable constraints, inside,
not), put them in a YAML rule file and run ast-grep scan -r rule.yml. See
references/rules.md for the rule patterns this review relies on.
Evidence output
Record:
dimension: structural.source: ast-grep command, language, pattern/rule file, searched scope, and version when parser behavior is in doubt.facts: matched file:line refs or confirmed zero-match scope.limits: parse errors, unsupported language, regex fallback, or lack of semantic reachability.
What ships with it
1 file 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 · 107 lines · 102 tokens per session scan A 4a233dec7c94
tools-ast-grep is a skill published in the GitHub repository alexei-led/architect (2 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,031 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 2026-08-31.
Other skills, from other repositories
bug-detective
This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.
grace-fix
Debug and fix issues in a GRACE 4 project using .grace semantic navigation, assertions, and verification evidence.
systematic-debugging
A four-phase method for investigating software bugs and test failures before changing code. It focuses on finding and confirming the underlying cause.
bensz-collect-bugs
A process for recording bugs caused by defects in Bensz skills. It stores a structured local report and can publish one only when the user explicitly asks.
bug-fix-protocol
8-step disciplined bug-fix protocol that treats every production bug as two failures — the code defect itself and the testing system that allowed it through. Use when fixing a production bug, investigating a regression, writing a post-mortem, or auditing a missed defect. Triggers on "fix this bug", "production bug"…
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.