ane - structured code operations

VerifiedCaution

Use ane for all file exploration, reading, and editing with chord commands. Prefer ane over builtin tools like grep, sed, and cat.

Sby Skills Guide Bot
DevelopmentAdvanced
8/6/2026
Claude CodeCursorWindsurfCodex
#code-editing#code-navigation#cli#file-operations#structured-editing

Recommended for

Automated summary

Wraps file reading, searching, and editing into a single `ane exec` command driven by a four-part "chord" grammar (action, positional, scope, component).

Strengths

  • One consistent grammar covers reading (Yank), symbol discovery (List), and edits (Change, Delete, Replace, Append, Prepend, Insert)
  • Targeting is by named symbol (function, variable, struct, member) instead of fragile regexes or line numbers
  • Accepts `-` to read an argument from stdin and writes results to stdout with an explicit 0/1 exit code
  • Replaces grep, sed, cat, and builtin read tools with one entry point

Limitations

  • The four-letter chord syntax (e.g. `yefc`, `civv`) is hard to recall without the reference table at hand
  • Assumes the `ane` binary is installed and on the agent's PATH
  • The document does not state which languages the symbol parsing supports
When to use it

Use it when an agent needs to read or edit code at symbol granularity (function body, variable value, signature) reliably from the command line.

When not to use it

Skip it when `ane` isn't installed, or for bulk regex/text processing across many files where dedicated tools fit better.

Security analysis

Caution
Quality score86/100

The skill is a usage guide for a legitimate file-editing CLI and contains no destructive, exfiltration, obfuscated, or safety-disabling instructions. However, it strongly directs the agent to run a third-party binary for all file interactions, including edits and deletes, so it warrants caution rather than being treated as risk-free.

Findings
  • •No allowed-tools declared despite instructing shell execution of `ane exec` for file operations.
  • •Directs the agent to prefer a third-party CLI over builtin file tools for all reads, searches, and edits, including delete operations, which increases tool-trust/supply-chain risk.
How this analysis is made

Examples

Read a function body
Use ane to show me the body of the `main` function in src/main.rs
Rename a function
Rename the function getData to fetch in api.rs using ane, then show me the signature to confirm
List symbols before editing
List all function definitions in parser.rs with ane so we know what targets are available before changing anything

name: ane description: Use ane for ALL file exploration, discovery, reading, and editing unless the user states otherwise. ane exec <file> --chord "<chord>" handles reads (Yank), searches (List), and edits (Change, Delete, Replace, Append, Prepend, Insert). Prefer ane over builtin file tools and shell utilities like grep, sed, and cat.

ane — structured code operations via chords

Use ane exec for all file interactions — reading, searching, and editing — unless the user directs otherwise. Prefer over builtin tools and grep/sed/cat.

ane exec <file> --chord "<chord>" — exit 0 = success (output on stdout), exit 1 = error (stderr).

Chord grammar

4-part: Action + Positional + Scope + Component

| Part | Letters | |------------|---------| | Action | c=Change d=Delete r=Replace y=Yank a=Append p=Prepend i=Insert j=Jump l=List | | Positional | i=Inside e=Entire a=After b=Before n=Next p=Previous u=Until o=Outside t=To l=Last f=First 1-9=Count | | Scope | l=Line b=Buffer f=Function v=Variable s=Struct m=Member d=Delimiter | | Component | b=Beginning c=Contents e=End v=Value p=Parameters a=Arguments n=Name s=Self w=Word d=Definition |

Short form: 4 lowercase chars, e.g. cels = ChangeEntireLineSelf. Long form: ChangeEntireLineSelf.

Arguments

chord(target:name_or_line, value:"text", find:"pat", replace:"rep")

Include only what's needed. Any arg accepts - to read from stdin:

echo "new body" | ane exec file.rs --chord "cifc(target:main, value:-)"

Reading files (Yank)

Use Yank (y) to read file contents to stdout — replaces cat, head, and builtin reads.

ane exec f.rs --chord "yebs"                        # read entire file (use sparingly)
ane exec f.rs --chord "yels(target:5)"              # read line 5
ane exec f.rs --chord "yefc(target:main)"           # read function body
ane exec f.rs --chord "yefs(target:main)"           # read entire function incl. signature
ane exec f.rs --chord "yefn(target:main)"           # read function name only
ane exec f.rs --chord "yefd(target:main)"           # read function signature (no body)
ane exec f.rs --chord "yevs(target:count)"          # read variable declaration

Exploring code (List)

Use List (l) to discover symbols — replaces grep and builtin search. Output: line:col name per match. Always list before editing an unfamiliar file so you know what targets are available.

ane exec f.rs --chord "lefd"                        # list all function definitions (signatures)
ane exec f.rs --chord "lefn"                        # list all function names
ane exec f.rs --chord "levd"                        # list all variable definitions
ane exec f.rs --chord "lesd"                        # list all struct definitions
ane exec f.rs --chord "lemd"                        # list all member/field definitions

Editing

ane exec f.rs --chord "cels(target:3, value:\"new text\")"       # change line 3
ane exec f.rs --chord "dels(target:5)"                            # delete line 5
echo "x + 1" | ane exec f.rs --chord "civv(target:count, value:-)"    # change variable value
ane exec f.rs --chord "cifn(target:getData, value:\"fetch\")"   # rename function (identifier only)
echo "pub fn fetch(url: &str) -> Result<()>" | ane exec f.rs --chord "cefd(target:getData, value:-)"  # rewrite full signature

Append and Prepend (line scope)

For Line scope, After vs Entire controls whether a new line is created:

# aals — insert on a NEW LINE after the target line
ane exec f.rs --chord "aals(target:10, value:\"new line\")"

# aels — append INLINE at end of the target line (no newline)
ane exec f.rs --chord "aels(target:10, value:\" // comment\")"

# pbls — insert on a NEW LINE before the target line
ane exec f.rs --chord "pbls(target:10, value:\"// above\")"

# pels — prepend INLINE at start of the target line (no newline)
ane exec f.rs --chord "pels(target:10, value:\"/// \")"

Component guide: Name vs Definition

  • n (Name) — bare identifier only. cifn renames without touching the signature.
  • d (Definition) — full declaration (visibility + fn + name + params + return type), excluding body. cefd changes visibility or rewrites the signature. Do NOT use cifn for visibility/signature changes.
ane exec f.rs --chord "cifn(target:foo, value:\"bar\")"           # fn foo() → fn bar() (rename only)
ane exec f.rs --chord "cefd(target:foo, value:\"pub fn foo()\")"  # fn foo() → pub fn foo() (visibility)

Efficiency: use the narrowest scope

Do not default to yebs (read entire file). Prefer targeted reads and edits:

  1. Discover first: run lefd or lefn to find function names/signatures before reading or editing.
  2. Read narrow: use yefc(target:fn_name) to read one function body, or yels(target:N) for one line. Only use yebs when you genuinely need the whole file.
  3. Edit narrow: use cifc(target:fn_name, value:-) to replace one function body. Avoid cebs (replace entire buffer) unless truly rewriting the whole file.
  4. Yank before changing: run yefc to understand what you're replacing before piping new content into cifc.

Narrow scopes produce less output, consume fewer tokens, and reduce the risk of unintended changes.

Notes

  • target: — line number (0-indexed) for Line scope, symbol name for LSP scopes (Function, Variable, Struct, Member).
  • LSP scopes require a language server. Line, Buffer, Delimiter do not.
  • Pipe stdin with value:- for multiline replacement text.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/ane-structured-code-operations-msh3urzd' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/ane-structured-code-operations-msh3urzd/download' --output '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md.part' && mv '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md.part' '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md' && test -s '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ane' && cp -R '.skill-downloads/ane-structured-code-operations-msh3urzd' '.claude/skills/ane'

Cursor
test -f '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md' && test -s '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/ane' && cp -R '.skill-downloads/ane-structured-code-operations-msh3urzd' '.cursor/skills/ane'

Codex
test -f '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md' && test -s '.skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/ane' && cp -R '.skill-downloads/ane-structured-code-operations-msh3urzd' '.agents/skills/ane'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/ane-structured-code-operations-msh3urzd'

openskills read 'ane-structured-code-operations-msh3urzd'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/ane-structured-code-operations-msh3urzd/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills