- Home
- Skills
- Agents & Orchestration
- Progressive Context Slicer
Works with the AI Agents you already use
Progressive Context Slicer
The habit that works is progressive: outline, then slice only what you need.
Free
Progressive Context Slicer
Example session with this skill installed
Use progressive-context-slicer to outline the 60,004-line file big.js (limit 5), slice symbol fn19999 without loading the rest of the file, and outline headings in d.md.
- Read your context and instructions
- Compiled the progressive context slicer
Real output from running the packaged scripts on small fixtures.
1. node file_outline_slicer.mjs outline big.js --limit 5 (a 60,004-line file)
$ node file_outline_slicer.mjs outline big.js --limit 5
big.js: 60004 lines, 1357840 bytes, type js
1 export function fn0(a) {
4 export function fn1(a) {
7 export function fn2(a) {
10 export function fn3(a) {
13 export function fn4(a) {
... 19997 more rows hidden (raise --limit)
(exit 0)
2. node file_outline_slicer.mjs slice big.js --symbol fn19999
$ node file_outline_slicer.mjs slice big.js --symbol fn19999
59998 export function fn19999(a) {
59999 return a + 19999; // note 日本語
60000 }
(exit 0)
3. node file_outline_slicer.mjs outline d.md
$ node file_outline_slicer.mjs outline d.md
d.md: 11 lines, 57 bytes, type md
1 # T
7 ## Sec
10 ## Other
(exit 0)
Connects securely to your tools. The creator never sees your data.
About this skill
Read a big file in layers, not all at once
Opening a 60,000-line file to read one function wastes context and buries the answer. The habit that works is progressive: outline, then slice only what you need. This free skill gives an agent that habit as one script.
Each skill ships one self-contained Node.js script (Node 18+, standard library only). It prints findings or results with a fix, and exits non-zero when the gate fails. Add --json for machine-readable output.
The skill
1. progressive-context-slicer outlines and slices large files:
- outline of functions, classes, headings or JSONL rows with line numbers
- slice by exact line range or by symbol name, with optional context lines
- find a string and read only the lines around it
- output capped by bytes and rows; streams files in chunks, so size is not a limit
Built for agents and for review
- Single file per skill, standard library only: copy one script anywhere and run it
- Works when the skill is loaded through the Agensi MCP: write the script to a temporary file, run it, delete it
- No network access, no shell commands, no environment reads
- Exit code and counts you can quote as evidence
What is in the ZIP
- README.md
- shared/verification-principles.md
- skills/progressive-context-slicer/scripts/file_outline_slicer.mjs
- skills/progressive-context-slicer/SKILL.md
Line-based symbol detection may miss complex nested patterns or non-standard declarations. Reads files only; no write capabilities. JSONL outline shows keys, not values.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
Requires