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/sightmap/sightmap/agents-mdgit clone --depth 1 https://github.com/sightmap/sightmapWhat 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 | $0.01964 | $0.01964 |
| Opus 5 | $0.00982 | $0.00982 |
| Sonnet 5 | $0.00393 | $0.00393 |
| Haiku 4.5 | $0.00196 | $0.00196 |
Grade A, and why
sightmap 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents working in this repository. This is the monorepo for the open Sightmap project: the specification, its reference implementation, and both websites.
This file is maintained as the repo is assembled. Areas are landing incrementally (see
PLAN.md); sections appear as their code arrives.
Repository layout
| Path | Stack | What it is |
|---|---|---|
spec/ |
Markdown + JSON Schema | Normative specification, SEP process, conformance fixtures. Source of truth. |
go/ |
Go | Reference implementation: sightmap CLI + go get-able library. npm: @sightmap/sightmap. |
skills/ |
Markdown | Canonical agent skills (sightmap-authoring, sightmap-browser). Installable as a plugin, embedded in the CLI, and vendored downstream. |
docs/ |
Mintlify | Documentation site (docs.sightmap.org). |
web/ |
React + Vite | Marketing landing page (sightmap.org). |
Each area is self-contained. go.mod lives only under go/; web/ has its own
package.json and netlify.toml; docs/ is configured by docs.json.
Golden rule: the spec is the source of truth
spec/v1/ (the human-readable schema.md + the machine-readable
sightmap.schema.json) is normative. Docs, websites, and the implementation
describe or implement it — when any of them disagree with spec/, spec/ wins.
Never change spec semantics without an SEP (spec/seps/).
Working in each area
spec/
- Changes to spec semantics (fields, matching, merge rules) require an SEP. Small wording/example fixes can be a plain PR.
- Keep
schema.md,sightmap.schema.json, andspec/v1/examples/in sync in one change.
go/ (module github.com/sightmap/sightmap/go)
go test ./...fromgo/.cmd/sightmap/is the binary; library packages (match,sel,comps, …) at the module root.- Downstream consumers import the library directly, so treat exported names as public API.
go/skills/<name>/is a generated, committed copy of the canonicalskills/(see below) — never hand-edit it.
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.
- 2d ago First seen · 136 lines · 1,964 tokens per session scan A 89b959ba67b0
sightmap AGENTS.md is an instructions file published in the GitHub repository sightmap/sightmap (55 stars, last pushed 3d ago), licensed MIT. It adds 1,964 tokens to every session, about $0.0098 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.