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/tdiderich/kazam/agents-mdgit clone --depth 1 https://github.com/tdiderich/kazamWrote 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.
[](https://agentmods.dev/instructions/tdiderich/kazam/agents-md)<a href="https://agentmods.dev/instructions/tdiderich/kazam/agents-md"><img src="https://agentmods.dev/badge/instructions/tdiderich/kazam/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01916 | $0.01916 |
| Opus 5 | $0.00958 | $0.00958 |
| Sonnet 5 | $0.00383 | $0.00383 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
kazam 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 3d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - developing kazam
For the YAML authoring guide (what kazam agents prints), see AGENTS.md.template.
Commands
cargo test --release --all-targets # CI gate (always --release)
cargo fmt --all --check # CI gate
cargo clippy --release --all-targets -- -D warnings # CI gate; warnings = error
cargo build --release # full build
./target/release/kazam dev docs --port 3002 # live-edit the docs site
CI runs these four jobs in parallel: test, fmt, clippy, cargo-audit.
Architecture
Single Rust binary. No workspace, no features, no build script. ~7 direct crates.
src/
main.rs CLI entry (clap derive): build, dev, init, agents, wish, track, ctx, board, workspace
types.rs All YAML-facing serde structs (SiteConfig, Page, Component, …)
theme.rs Theme tokens + STATIC_CSS (giant const string)
render/
mod.rs Page render orchestration
components.rs Per-component render fns + dispatch match at top
shells.rs Shell chrome (standard, document, deck)
scripts.rs Bundled inline JS (deck nav, tabs, accordion, auto-fit)
charts.rs SVG chart rendering (pie, bar, timeseries)
slug.rs Anchor slug generation (used by section + header)
build.rs Batch build (yaml → html, copy assets)
dev.rs Watch + serve (notify + tiny_http)
init.rs kazam init scaffolding (KAZAM_YAML / INDEX_YAML / AGENTS_MD consts)
agents.rs kazam agents subcommand
freshness.rs Staleness computation (freshness: → banner + stale.md)
links.rs Link graph (orphan pages + broken internal hrefs)
llms.rs llms.txt emission
minify.rs Release-mode HTML/CSS/JS minification
icons.rs Bundled lucide icon SVGs
wish/
mod.rs kazam wish dispatch (list, scaffold, grant, yolo)
deck.rs Deck wish (workspace + prompt generation)
brief.rs Brief wish
workspace.rs .kazam/ directory init, config read/write, atomic YAML persistence
id.rs Hash-based ID gen (kz-XXXX, no rand dep)
board.rs kazam board - live dashboard rendering .kazam/ state
server.rs Shared HTTP helpers: port binding, browser launch, responses, shutdown
open.rs kazam open, single-file browser viewer/editor for md/yaml/json
show.rs kazam show, single-file terminal pretty-printer for md/yaml/json
track/
mod.rs kazam track CLI dispatch (11 subcommands)
types.rs Task, TaskStatus, TaskType, LogEntry, LogSeverity
store.rs YAML read/write for tasks + log
graph.rs Ready algorithm, dependency validation, cycle detection
ctx/
mod.rs kazam ctx CLI dispatch (10 subcommands)
types.rs FileEntry, AnatomyStore, Learning, BugEntry
scan.rs Project file walker, token estimation, anatomy diff
hooks.rs Agent hook install/uninstall, shell script templates
docs/ The hosted docs site (itself a kazam site)
examples/kb/ Example site used by integration tests
tests/integration.rs E2e: invokes the binary, builds sites, asserts on HTML output
AGENTS.md.template Authoring guide bundled via include_str! → kazam agents / kazam init
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.
- 3d ago First seen · 130 lines · 1,916 tokens per session scan A 9688a8dfc9b0
kazam AGENTS.md is an instructions file published in the GitHub repository tdiderich/kazam (5 stars, last pushed 4d ago), licensed MIT. It adds 1,916 tokens to every session, about $0.0096 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.