agentmods.dev

contextception AGENTS.md

An instruction file for AI agents working on Contextception, a Go program that builds and analyzes code dependency indexes. It explains how to get oriented, run checks, follow code conventions, and understand the main architecture.

In plain words
What is it for?
Helping agents build, test, lint, and extend Contextception’s code-indexing and dependency-analysis components.
Why use it?
It gives agents the project-specific commands and rules needed to make safe, consistent changes. It also explains the pipeline that extracts and resolves imports across several programming languages.

Instructions file for CodexOpenCode

6 1mo ago A scan 610 tokens original MIT
View the source file kehoej/contextception
Install

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.

agentmods
npx agentmods add instructions/kehoej/contextception/agents-md
Clone the repo
git clone --depth 1 https://github.com/kehoej/contextception

Made for: Codex, OpenCode.

Per session 610 This file is loaded in full into every session.
When invoked 610 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00610 $0.00610
Opus 5 $0.00305 $0.00305
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured yesterday against content hash 717ac195b84e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contextception AGENTS.md 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 yesterday.

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.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Guidelines

When working on this codebase:

Getting Oriented

  1. Read CLAUDE.md for project overview and tech stack
  2. Read docs/ARCHITECTURE.md for the full architecture with diagrams
  3. Run contextception status to check index health

Development Commands

make build      # Build binary
make test       # Run all tests (includes race detector in CI)
make lint       # Run golangci-lint
make check      # Run vet + lint + test in one command
make coverage   # Generate HTML coverage report

Code Conventions

  • Standard Go conventions: gofmt, go vet, golangci-lint
  • Error handling: wrap errors with fmt.Errorf("context: %w", err)
  • No panic() — always return errors
  • Parameterized SQL queries only (never string concatenation)
  • Test files go alongside source: foo_test.go next to foo.go
  • Integration test fixtures go in testdata/

Architecture Quick Reference

internal/extractor/   Language-specific import extraction (Python, TS, Go, Java, Rust)
internal/resolver/    Module specifier → file path resolution (per-language)
internal/indexer/     Scan → extract → resolve → store pipeline
internal/analyzer/    Dependency graph traversal, scoring, categorization
internal/change/      PR/branch diff impact analysis
internal/db/          SQLite storage (migrations in internal/db/migrations/)
internal/mcpserver/   MCP server with 9 tools
internal/history/     Usage tracking, feedback storage, analytics queries
internal/session/     Claude Code session parser (discover, adoption)

Adding a New Language

  1. Create extractor in internal/extractor/<lang>/ implementing extractor.Extractor
    • Extensions() must return the file extensions (e.g., []string{".cs"})
    • This is enforced by the interface. The contextception extensions command automatically picks up new extensions.
  2. Create resolver in internal/resolver/<lang>/ implementing resolver.Resolver
  3. Register both in internal/indexer/indexer.go (instantiate extractor + resolver in NewIndexer)
    • Also add the extractor to internal/cli/extensions.go so contextception extensions includes it
  4. Add test fixtures in testdata/
  5. Verify: contextception extensions should list your new file extensions
  6. See existing implementations (e.g., internal/extractor/python/) for reference

Read the full file on GitHub · 62 lines

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. yesterday First seen · 62 lines · 610 tokens per session scan A 717ac195b84e

Subscribe to this mod's changes

contextception AGENTS.md is an instructions file published in the GitHub repository kehoej/contextception (6 stars, last pushed 1mo ago), licensed MIT. It adds 610 tokens to every session, about $0.0030 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 2026-08-31.

Code reviewPlanningTestingcode-contextdependency-graphdeveloper-toolsgomcpstatic-analysis
Related

Other instructions, from other repositories

semgrep AGENTS.md

AGENTS.md instructions for semgrep/semgrep, covering semgrep oss codebase overview, architecture, key concepts, python-to-ocaml migration strategy and developer setup.

semgrep/semgrep · 1,923 tokens

semgrep CLAUDE.md

Claude Code instructions for semgrep/semgrep, a project described as: Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.

semgrep/semgrep · 5 tokens

serpentine CLAUDE.md

Claude Code instructions for serpentine-parser/serpentine, covering project, dev environment, features, reading files and key conventions & patterns.

serpentine-parser/serpentine · 1,014 tokens

ollama CLAUDE.md

Instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.

ollama/ollama · 21 tokens

azure-sdk-for-go go-code.instructions.md

Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.

Azure/azure-sdk-for-go · 755 tokens

gorest AGENTS.md

Instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.

pilinux/gorest · 5,194 tokens