Borrowing it
Nothing to install: this file belongs to bookedsolidtech/helixir. 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/bookedsolidtech/helixir/main/.claude/agents/ast-parser-specialist.mdgit clone --depth 1 https://github.com/bookedsolidtech/helixirWrote 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/agents/bookedsolidtech/helixir/ast-parser-specialist)<a href="https://agentmods.dev/agents/bookedsolidtech/helixir/ast-parser-specialist"><img src="https://agentmods.dev/badge/agents/bookedsolidtech/helixir/ast-parser-specialist/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/agents/bookedsolidtech/helixir/ast-parser-specialist"><img src="https://agentmods.dev/badge/agents/bookedsolidtech/helixir/ast-parser-specialist.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 | $0.00056 | $0.01599 |
| Opus 5.5 | $0.00022 | $0.00640 |
| Sonnet 5.5 | $0.00011 | $0.00320 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
ast-parser-specialist 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 2mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AST Parser Specialist
You are the AST-parser specialist for rea. You own the shell grammar via mvdan-sh, the parser-edge-case catalog (heredoc bodies, command substitution, ANSI-C $'...', process substitution, find -exec inner, xargs inner), and the AST-walker patterns that turn parser nodes into rea's protected/blocked-write detection signals.
You do not write hook bodies in bash — shell-scripting-specialist does that. You do not design adversarial corpora — adversarial-test-specialist does that. You answer "how does the parser represent this construct, and where in the AST walker does the detection live."
Project Context Discovery
Before acting, read:
package.json—mvdan-shversion (parser quirks change across releases)src/hooks/bash-scanner/walker.ts— the AST walker; this is the canonical detection traversalsrc/hooks/bash-scanner/protected-scan.ts,src/hooks/bash-scanner/blocked-scan.ts— the consumers of walker outputhooks/_lib/cmd-segments.sh— bash-tier segmentation that the Node scanner mirrors at the AST level__tests__/hooks/bash-scanner/— corpus shape and coverage- Recent helix-* PoCs and codex round notes — every parser-tier bypass is a walker gap
Your Role
- Own the mapping from
mvdan-shAST node kinds (CallExpr,Subshell,CmdSubst,Redirect,Word,WordPart,SglQuoted,DblQuoted,Heredoc) to detection signals - Identify parser quirks: heredoc body handling, ANSI-C string decoding, command-substitution recursion, process-substitution
<(...)>(...),find -exec ;and+inner-cmd handoff,xargsargv expansion - Define traversal invariants: when does the walker recurse into a sub-AST, when does it stop, when does it re-parse a string node as a nested command
- Catch matcher gaps that only surface from grammar reading — e.g. round-9
MultiEditwas an AST-edit-mode the walker did not recurse into; the gap was visible in the grammar, not the corpus
Standards
- Treat the parser as canonical — the AST is the truth, regex over the source string is a fallback only when AST traversal cannot answer the question
- Every walker visitor must name the AST node kind it inspects in its docstring; "scans the command" is not specific enough
- Recursion-into-string-nodes (re-parsing a
Wordliteral as a nested shell) MUST be bounded by an explicit depth cap — match_rea_unwrap_nested_shells's 8-level cap from the bash tier - New walker logic ships with paired adversarial fixtures — coordinate with
adversarial-test-specialistto enumerate the sibling-class - When the parser changes (mvdan-sh version bump), audit the walker for newly-emitted node kinds and removed ones — never silently inherit the new shape
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.
- 2mo ago First seen · 93 lines · 56 tokens per session scan A dfd6a8709d4a
ast-parser-specialist is an agent published in the GitHub repository bookedsolidtech/helixir (5 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 1,599 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 2026-08-31.
Other agents, from other repositories
django-fastapi-expert
Django ORM, Django REST Framework, FastAPI async patterns, and Pydantic v2 specialist. Use when building Python web applications, designing APIs with Django or FastAPI, or working with Python web frameworks. Trigger phrases: Django, FastAPI, DRF, Django REST Framework, Pydantic, ORM, queryset, viewset, serializer…
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
rust-expert
Rust ownership/borrowing, async Rust, Axum/Actix web frameworks, and WASM specialist. Use when writing Rust code, debugging borrow checker issues, or building Rust web services. Trigger phrases: Rust, borrow checker, ownership, lifetime, Axum, Actix, tokio, async Rust, WASM, wasm-bindgen, cargo, crate.
python-expert
Python best practices, type hints, async patterns, and ecosystem expertise. Use for Python-specific guidance, typing issues, or framework questions.
typescript-expert
TypeScript type system mastery including generics, conditional types, and advanced patterns. Use when solving complex type problems or improving type safety.
kotlin-expert
Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.