What is extend-cel-schema?

A skill for adding new searchable attributes to file-search-on's CEL query language. CEL is a language used to write expressions that filter or inspect data.

Extending the file-search-on schema, updating the required Go call sites, and running an audit that detects mismatches between them.

It keeps the attribute declaration, runtime value lookup, and schema documentation aligned so queries do not fail because one part was missed.

How richardwooding/file-search-on configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to richardwooding/file-search-on. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/richardwooding/file-search-on/main/.claude/skills/extend-cel-schema/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/richardwooding/file-search-on

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/richardwooding/file-search-on/extend-cel-schema/github.svg)](https://agentmods.dev/skills/richardwooding/file-search-on/extend-cel-schema)

Your own site

<a href="https://agentmods.dev/skills/richardwooding/file-search-on/extend-cel-schema"><img src="https://agentmods.dev/badge/skills/richardwooding/file-search-on/extend-cel-schema/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/richardwooding/file-search-on/extend-cel-schema"><img src="https://agentmods.dev/badge/skills/richardwooding/file-search-on/extend-cel-schema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,555 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00138	$0.01555
Opus 5.5	$0.00055	$0.00622
Sonnet 5.5	$0.00028	$0.00311
Haiku 4.5	$0.00014	$0.00155

Measured 2mo ago against content hash f0445357fe0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

extend-cel-schema 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit_attributes.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/extend-cel-schema/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extend CEL Schema

Every CEL-visible attribute in file-search-on must be declared, resolvable, and documented — three call sites that must move together. Drift between them produces a runtime error (no such attribute: foo) the moment a CEL expression references the missing piece — go build will not catch it. This skill makes the invariant explicit and ships an audit script that reports drift.

The invariant

A CEL-visible attribute must be declared, resolvable, and documented. Drift produces a runtime error (no such attribute: foo) the moment a CEL expression references the missing piece — go build will not catch it.

Where	What goes there	Failure mode if missing
`internal/celexpr/env.go` — `cel.Variable("foo", cel.<Type>Type)` inside `New`	Declares the variable to cel-go	Compile error: `undeclared reference to 'foo'`
`internal/celexpr/activation.go` — resolution in `(fileAttrsActivation).ResolveName`, via either* a `case "foo":` returning a typed `FileAttributes` field or a key in the `zeroDefaults` map	How the attribute's value is produced at evaluation time	Runtime error: `no such attribute: foo`
`internal/celexpr/schema.go` — entry in the right `AttributeDoc` slice	Drives both `--list` output and the MCP `list_attributes` tool	Attribute is invisible to humans and to MCP clients

How resolution works (post-2024 refactor). ResolveName(name) is a single switch:

Typed fields — common scalars (name, path, size, …) and every is_* predicate / md5 / similarity / … resolve via a case "foo": return a.attrs.Foo, true that reads a FileAttributes struct field. No default needed; the field is always present.
Type-specific / front-matter attributes — fall through the switch to a verbatim Extra[name] lookup, then to zeroDefaults[name]. There is no rename switch anymore: the content type's Attributes() map must emit the final CEL name directly (e.g. emit img_width, not width; emit json_kind, not kind). The zeroDefaults entry supplies the value for files that didn't emit the key.

Read the full file on GitHub · 60 lines

Files

What ships with it

2 files 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.

Changes

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 · 60 lines · 138 tokens per session scan A f0445357fe0b

Subscribe to this mod's changes

extend-cel-schema is a skill published in the GitHub repository richardwooding/file-search-on (5 stars, last pushed 4d ago), licensed MIT. It adds 138 tokens to every session and 1,555 once invoked, about $0.0006 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.

Backend and APIs cel cli content-detection file-search go mcp

extend-cel-schema next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
extend-cel-schemarichardwooding/file-search-on	Skill	5	4d ago	MIT	A	138	Claude Code
goericrisco/rsc-harness	Skill	503	2d ago	MIT	A	86	Claude Code, Codex
go-docspledgeandgrow/pledge-skills	Skill	10	3mo ago	MIT	A	36	Claude Code, Codex
golang-samber-doalexastrum/skl	Skill	10	4mo ago	MIT	A	74	Claude Code
goznlgis/opengis-skills	Skill	76	10d ago	MIT	D	88	Claude Code, Codex
cartograph-use-casejeunessegamesee/clew	Skill	0	2mo ago	MIT	A	54	Claude Code, Codex
golang-grpcalexastrum/skl	Skill	10	4mo ago	MIT	A	72	Claude Code

file-search-on: Skill for Claude Code