agentmods.dev

context-sherpa: Skill for Claude Code

.agents/skills/architectural-grounding/SKILL.md

Architectural Grounding (Large File Discovery) is a skill for Claude Code, Codex from hackafterdark/context-sherpa. It costs 29 tokens per session (292 once invoked), scanned A, original, MIT.

A method for understanding large program files by first examining their structure and then reading only the relevant parts. It is intended for entry-point files longer than 300 lines.

In plain words
What is it for?
It helps locate important functions and data structures, trace a feature's flow, and inspect selected line ranges in large files.
Why use it?
It reduces the amount of source code an agent must read while preserving enough context to explain how a feature works.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is hackafterdark/context-sherpa's own configuration. It tells Claude Code and Codex how to work on context-sherpa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything context-sherpa configures →

not rated 26repo +1 7mo ago A scan 29 tokens original MIT
View source ↗ hackafterdark/context-sherpa
Reuse

Borrowing it

Nothing to install: this file belongs to hackafterdark/context-sherpa. 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/hackafterdark/context-sherpa/main/.agents/skills/architectural-grounding/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hackafterdark/context-sherpa

Made for: Claude Code, Codex.

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.

agentmods badge for Architectural Grounding (Large File Discovery)

README.md
[![agentmods](https://agentmods.dev/badge/skills/hackafterdark/context-sherpa/architectural-grounding/github.svg)](https://agentmods.dev/skills/hackafterdark/context-sherpa/architectural-grounding)
Your own site
<a href="https://agentmods.dev/skills/hackafterdark/context-sherpa/architectural-grounding"><img src="https://agentmods.dev/badge/skills/hackafterdark/context-sherpa/architectural-grounding/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.

agentmods 80×15 button for Architectural Grounding (Large File Discovery)

Your own site · 80×15
<a href="https://agentmods.dev/skills/hackafterdark/context-sherpa/architectural-grounding"><img src="https://agentmods.dev/badge/skills/hackafterdark/context-sherpa/architectural-grounding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 292 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00292
Opus 5.5 $0.00012 $0.00117
Sonnet 5.5 $0.00006 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 2mo ago against content hash 540b38048375, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Architectural Grounding (Large File Discovery) 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.

.agents/skills/architectural-grounding/SKILL.md · 21 lines

What it actually says

Skill: Architectural Grounding

Goal: Understand the responsibility of a complex file without reading the raw source.

Execution Pattern

  1. Metadata Triage: If a file is known to be large (e.g., app.go, main.go, server.go), call list_symbols_in_file with distill: true immediately.
  2. Component Isolation: Identify the 2-3 specific methods or structs in the distilled summary that are relevant to the query.
  3. Symbolic Zoom: Call search_definitions or get_symbol_map on those specific components to find their definitions.
  4. Surgical Read: ONLY call read_file or view_file for the specific line ranges identified in step 3. NEVER read more than 100 lines at once.

Success Metric

The agent should be able to explain the "Flow" of a feature (like Database Init) while having read fewer than 15% of the total lines in the file.

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.

  1. 2mo ago First seen · 21 lines · 29 tokens per session scan A 540b38048375

Subscribe to this mod's changes

Architectural Grounding (Large File Discovery) is a skill published in the GitHub repository hackafterdark/context-sherpa (26 stars, last pushed 7mo ago), licensed MIT. It adds 29 tokens to every session and 292 once invoked, about $0.0001 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 2026-08-30.

Debuggingaimcpmcp-server
Related

Architectural Grounding (Large File Discovery) compared with skills from other repositories

Architectural Grounding (Large File Discovery) next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Architectural Grounding (Large File Discovery)hackafterdark/context-sherpaSkill267mo agoMITA29Claude Code, Codex
chrome-devtools-cliChromeDevTools/chrome-devtools-mcpSkill55ktodayApache-2.0A31Claude Code
n8n-error-handlingczlonkowski/n8n-mcpSkill23ktodayMITA128Claude Code, Codex
n8n-validation-expertczlonkowski/n8n-mcpSkill23ktodayMITA91Claude Code, Codex
agentcore-investigationawslabs/mcpSkill9.9kyesterdayApache-2.0A52Claude Code, Codex
analyze-dumpsvnscha/mcp-windbgSkill1.7k10d agoMITA56Claude Code
memorix-troubleshootingAVIDS2/memorixSkill9193d agoApache-2.0A36Claude Code