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/thiagokokada/gitk-go/agents-mdgit clone --depth 1 https://github.com/thiagokokada/gitk-goWrote 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/thiagokokada/gitk-go/agents-md)<a href="https://agentmods.dev/instructions/thiagokokada/gitk-go/agents-md"><img src="https://agentmods.dev/badge/instructions/thiagokokada/gitk-go/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 | $0.00835 | $0.00835 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
gitk-go 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 4d 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.
What it actually says
Automation Notes
This project occasionally uses AI assistance. To keep contributions consistent, agents should follow these rules:
- Keep UI logic testable. Add pure helpers near their owner and cover them with unit tests.
- Treat
cmdandinternal/guias UI orchestration layers. Core Git behavior belongs ininternal/git. - Use
go test ./...,go fmt, andgo vet ./...before sending changes whenever the environment allows it. - README and AGENTS should stay ASCII-only and concise.
- Keep lines under 120 characters (enforced by golangci-lint).
- If a function returns multiple values of the same type, use named return values.
- Dot imports are only allowed for
modernc.org/tk9.0. - Describe sandbox or permission issues observed while running commands so maintainers can reproduce locally,
but ignore
nice(5) failed: operation not permitted. - Keep GUI assets (icons, images, etc.) inside
internal/gui/assetsand reference them there when usinggo:embed. - Group related controller/state fields into dedicated structs instead of leaving long flat structs.
- When working with mutexes, prefer
defer mu.Unlock()immediately after locking unless there is a strong reason not to. - Prefer
slog/loginstead oflogfor logging. - Prefer tests co-located with the implementation (e.g.
internal/gui/filter_test.goforfilter.go) instead of creating per-feature test filenames. - Always run tests with
GOCACHEset to avoid sandbox issues:env GOCACHE="$PWD/.gocache" go test ./.... - Avoid abstraction-only wrappers. Add methods when they encode behavior, enforce invariants, or coordinate multiple fields. Prefer package functions over methods when no receiver state is used.
- Keep Tk widget construction, bindings, tag names, dialogs, menu setup, and widget guards in
internal/gui/view. - Keep controller code focused on service calls, async scheduling, persistence, status text, and model/view coordination. Do not leave direct widget field checks in controllers when a view helper can own them.
- Keep pure state transitions, selection policy, diff view models, and display preparation in
internal/gui/model. - Do not duplicate constants or helpers across
internal/gui,model, andview; promote one owner instead. - Prefer typed
modernc.org/tk9.0APIs overtkutil.Evalf. UseEvalfonly when the wrapper lacks the needed Tk subcommand or behavior. - Do not remove an
Evalfworkaround orXXXcomment by inspection alone. Reproduce the GUI path or add focused coverage that proves the replacement behaves the same. - Keep unavoidable
Evalfcalls narrow and documented at the call site, including why the typed wrapper is not sufficient. - Do not amend or rewrite existing commits unless the user explicitly asks for history rewriting.
- Model-owned maps should be initialized by their state constructors when nil does not represent a real lifecycle state. Tests should use those constructors instead of relying on raw zero values.
- Required Tk widget assumptions only hold after
view.App.Build. Startup code may activate themes before build, but widget-specific style refreshes must run after widgets are constructed. - Treat initialized commit entries as value data.
git.Entryshould own agit.Commitvalue, and GUI/model collections should use[]git.Entryunless nil is a real lifecycle state. - Keep backend stream internals pointer-based when useful, but reject nil commits at the service boundary before creating entries. Model helpers should use hash/index validity checks for recoverable missing-row cases.
- Do not add helper functions that only restate direct field access, such as wrapping
entry.Commit.Hash, unless they enforce an invariant or coordinate more than one field.
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.
- 4d ago First seen · 48 lines · 835 tokens per session scan A 2537905dbea8
gitk-go AGENTS.md is an instructions file published in the GitHub repository thiagokokada/gitk-go (121 stars, last pushed 7d ago), licensed MIT. It adds 835 tokens to every session, about $0.0042 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
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.