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/craigjmidwinter/katra/agents-mdgit clone --depth 1 https://github.com/craigjmidwinter/katraWrote 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/craigjmidwinter/katra/agents-md)<a href="https://agentmods.dev/instructions/craigjmidwinter/katra/agents-md"><img src="https://agentmods.dev/badge/instructions/craigjmidwinter/katra/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 | $0.01562 | $0.01562 |
| Opus 5 | $0.00781 | $0.00781 |
| Sonnet 5 | $0.00312 | $0.00312 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
katra 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
katra is a committed, markdown-native dev log: entries live as markdown files
under katra/, a draft is an entry with no commit hash, and stamping (adding
the hash + diffstat) is what publishes it. Around the log sits a node model —
tasks, epics, decisions, articles — and a viewer/hub that renders it all.
Written in Go; two binaries, katra (CLI) and katra-mcp (MCP server).
Commands
All green on a clean checkout — if one isn't, that is a bug worth reporting.
make all # both binaries into ./bin/ (never `go build -o katra` — see below)
go test ./... # full suite; CI runs it with -race
golangci-lint run # config in .golangci.yml; falls back to: go vet ./... && gofmt -l .
make build builds only ./bin/katra; make build-mcp builds only
./bin/katra-mcp.
Harness-neutral Katra workflow
The committed CLI workflow is canonical; a Claude skill or hook may automate it but must not be the only place it is taught. In every harness:
- Inspect durable work with
katra task list --status specced,katra task list --status doing, andkatra epic rollup. - For a larger outcome, create an epic, then a child task with
katra epic new "…"andkatra task new "…" --epic <slug>. - When design is warranted, author a spec artifact and attach it with
katra task spec <task> <node-slug-or-repo-path>. Commit the artifact and task pointer together before implementation, verify the task isspecced, read the artifact, then runkatra task start <task>. - Before implementation edits, open the running chronicle with
katra new "…". Usekatra appendfor decisions and rejected alternatives,katra decidefor a durable choice, andkatra capture/comparefor at least one visual whenever the work can be shown. - Commit the bounded implementation. Publish with
katra stamp --closes <task> --commit; this closes and links the task and rolls up its epic. If the portable post-commit hook is installed, runkatra reconcile --close <task>before the implementation commit so the closure is already attached to the draft. - Finish with
katra doctor, task/epic status checks,katra list, and a clean working tree.
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 · 110 lines · 1,562 tokens per session scan A 65a13a8adb7f
katra AGENTS.md is an instructions file published in the GitHub repository craigjmidwinter/katra (0 stars, last pushed 6d ago), licensed MIT. It adds 1,562 tokens to every session, about $0.0078 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.