What is strike AGENTS.md?

A set of development instructions for Strike, a Go-based terminal interface for an AI coding agent. It documents the event engine, user interface, session logs, and required verification checks.

Finding the main parts of the codebase, formatting Go code, regenerating the web interface, running tests and static checks, building the program, and using race detection for sensitive changes.

It tells contributors which tests and build checks are required for different kinds of changes, including changes affecting permissions, sessions, or concurrency.

How jonathanung/strike configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to jonathanung/strike. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jonathanung/strike/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/jonathanung/strike

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jonathanung/strike/agents-md/github.svg)](https://agentmods.dev/instructions/jonathanung/strike/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/jonathanung/strike/agents-md"><img src="https://agentmods.dev/badge/instructions/jonathanung/strike/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jonathanung/strike/agents-md"><img src="https://agentmods.dev/badge/instructions/jonathanung/strike/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,507 This file is loaded in full into every session.

When invoked 2,507 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.02507	$0.02507
Opus 5.5	$0.01003	$0.01003
Sonnet 5.5	$0.00501	$0.00501
Haiku 4.5	$0.00251	$0.00251

Measured 12d ago against content hash d30463f7a70c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

strike 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 12d 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.

AGENTS.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

strike-cli

Go 1.26 agentic coding TUI. Engine emits protocol events; TUI consumes them. Sessions are JSONL event logs.

Verification (required before claiming done)

Tiers (skills test-and-validate / issue-handler follow this table — do not fork softer gates):

Tier	When	Local gate
A	Docs, skills, comments, markdown-only	`gofmt` if any `.go` touched; full suite not required
B	Normal Go / web / TUI (default)	`gofmt` → `go generate ./internal/frontend/tui/app` if `internal/frontend/tui/app/_src` changed → `make web-check` if `web/` changed → `make test && make vet && make build`
C	Trust boundary: tool, permission, auth, session, engine concurrency/turn, protocol wire, sandbox	Tier B + `go test -race ./... -count=1` + focused package tests first

CI (.github/workflows/ci.yml) always runs gofmt, TUI generate, web-check (when web present), build, vet, and go test -race ./.... Local race on every PR is redundant for tier A/B.

make test          # go test ./...
make vet           # go vet ./...
make build         # go build -o strike ./cmd/strike
make cover         # go test ./... -coverprofile=coverage.out (+ total %)
make cover-check   # cover + fail if total statements % < COVER_MIN (default 75)

Product smoke (user-visible cmd/engine/tui/session/auth): skill smoke / make run-echo. Releases: skill release.

Report exact commands and failing output verbatim. Do not claim green without running the tier gate.

Testing conventions

Standard library testing only — no testify/ginkgo/gomock.
Tests live next to source as *_test.go.
Prefer table-driven cases; use t.TempDir() and t.Setenv("HOME", ...) for isolation.
Mock only external boundaries (HTTP via httptest, clocks when needed). Never mock the unit under test.
Tool tests: allow-all Ask helper unless testing permission denial.
Provider tests: httptest.Server for wire format; use harness/provider/echo for offline engine loops.
TUI tests: reuse helpers from internal/frontend/tui/app/_src/app/app_test.go (updateApp, runAppCmd, etc.; package tests after go generate ./internal/frontend/tui/app).

Read the full file on GitHub · 134 lines

Changes

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.

12d ago Changed · -1 tokens per session d30463f7a70c
2mo ago First seen · 134 lines · 2,508 tokens per session scan A d81206b04fd2

Subscribe to this mod's changes

strike AGENTS.md is an instructions file published in the GitHub repository jonathanung/strike (5 stars, last pushed today), licensed Apache-2.0. It adds 2,507 tokens to every session, about $0.0100 per session on Opus 5.5. 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.

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).

microsoft/vscode · 9,715 tokens

strike: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

strike-cli

Verification (required before claiming done)

Testing conventions

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deno copilot-instructions.md