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 apmantza/pi-lens --skill pi-lens-write-tree-sitter-rulegit clone --depth 1 https://github.com/apmantza/pi-lensWrote 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/apmantza/pi-lens/pi-lens-write-tree-sitter-rule)<a href="https://agentmods.dev/skills/apmantza/pi-lens/pi-lens-write-tree-sitter-rule"><img src="https://agentmods.dev/badge/skills/apmantza/pi-lens/pi-lens-write-tree-sitter-rule/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/apmantza/pi-lens/pi-lens-write-tree-sitter-rule"><img src="https://agentmods.dev/badge/skills/apmantza/pi-lens/pi-lens-write-tree-sitter-rule.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 | $0.01230 |
| Opus 5 | $0.00020 | $0.00615 |
| Sonnet 5 | $0.00008 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
pi-lens-write-tree-sitter-rule 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 12d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing a pi-lens tree-sitter Rule
Drop path: rules/tree-sitter-queries/<language>/<id>.yml
Language dir is lowercase: typescript javascript tsx python go rust java csharp kotlin php ruby cpp c css
Project rules merge with built-ins (both run). To disable a language's built-ins: rename dir to <lang>-disabled/.
Minimal template
id: no-eval
severity: error
inline_tier: blocking # blocking | warning | review
language: typescript # lowercase, inferred from dir if omitted
message: "eval() is dangerous — use a safer alternative"
query: |
(call_expression
function: (identifier) @FN
(#eq? @FN "eval"))
metavars: [FN]
has_fix: false
S-expression query syntax
; Node with field
(call_expression
function: (identifier) @NAME
arguments: (arguments) @ARGS)
; Alternatives — ALL branches must use the SAME capture names
[
(function_declaration name: (identifier) @FN)
(arrow_function) @FN
]
; Predicates (inline)
(#eq? @NAME "fetch") ; exact match
(#match? @NAME "^on[A-Z]") ; regex match
Predicates via YAML (faster — runs in WASM)
predicates:
- type: eq # eq | match | any-of
var: "@FN"
value: "dangerousMethod"
- type: match
var: "@NAME"
value: "^(get|set)[A-Z]"
inline_tier
| Value | Effect |
|---|---|
blocking |
Blocks agent turn — 🔴 injected immediately |
warning |
Advisory only |
review |
Low-priority suggestion |
Gotchas
❌ Mixed capture names in [...] alternatives — zero matches, no error
[ (fn_decl name: (id) @NAME) (method body: (block) @BODY) ]
→ split into two separate [...] blocks
❌ Field value as alternative
right: [(identifier) (call_expression)] ← INVALID
→ use separate query blocks instead
❌ @lowercase captures — convention is @UPPER_SNAKE
@fn → @FN
✅ Find node kinds: use --debug-query CST in ast-grep playground
or https://tree-sitter.github.io/tree-sitter/playground
✅ Schema + autocomplete: rules/tree-sitter-queries/rule-schema.json
✅ Docs: docs/custom-rules.md
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.
- 12d ago First seen · 130 lines · 40 tokens per session scan A a02cc831dd0c
pi-lens-write-tree-sitter-rule is a skill published in the GitHub repository apmantza/pi-lens (405 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,230 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…