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.
npx agentmods add instructions/alejandro-cedeno-10/contextforge-cli/agents-mdgit clone --depth 1 https://github.com/alejandro-cedeno-10/contextforge-cliWhat 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 | $0.00549 | $0.00549 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
contextforge-cli 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ContextForge Agent Rules
Mission
Build and maintain a token-efficient CLI that generates:
- structural graphs
- context packs
- SDD specs
- implementation plans
Defaults
- Prefer deterministic analysis over LLM inference.
- Never reload the full repository if a graph or context pack already exists.
- Validate all machine-readable outputs against JSON Schema.
- Keep prompts short, explicit, and task-scoped.
- Prefer minimal diffs and minimal file touches.
Repo conventions
- Runtime: Node.js >= 22
- Package manager: pnpm
- Monorepo packages live under
packages/ - Generated artifacts live under
.contextforge/
Command policy
forge scanmust not call any LLM.forge graphshould stay deterministic by default.--force: rebuilds from scratch, ignoring scan-hash cache and per-file cache. Use it after editing the parser or to debug.--with-calls: opt-in detection ofcallsedges via regex. The default output never includescalls— keep it that way unless the consumer explicitly asked for them; the heuristic is noisier thanimports.- The per-file cache lives at
.contextforge/graph.cache.jsonand is invalidated automatically when the parser version bumps. Don't commit it.
forge contextmay summarize only when budget requires it.forge specprepares the input for OpenSpec — it does not duplicate OpenSpec's logic. WithopenspecCLI in PATH it delegates scaffolding toopenspec new change. Without it, the fallback emits the same modern format (### Requirement:+#### Scenario:) soopenspec validatepasses once the CLI is installed.forge implementdefaults to plan-only unless explicitly allowed to edit.
For agents working in this repo
Before reading files, read .contextforge/agent-context.md first — it lists
all available artifacts (graph, context-pack, spec-input, manifest) plus the
SDD recipe. Do not re-scan the repo if .contextforge/context-pack.json
already exists for the current task.
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.
- yesterday First seen · 61 lines · 549 tokens per session scan A 842e7d80e798
contextforge-cli AGENTS.md is an instructions file published in the GitHub repository alejandro-cedeno-10/contextforge-cli (0 stars, last pushed 3mo ago), licensed MIT. It adds 549 tokens to every session, about $0.0027 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.