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/jiangkoumo/agenttape/agents-mdgit clone --depth 1 https://github.com/jiangkoumo/agenttapeWhat 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 | $0.00793 | $0.00793 |
| Opus 5 | $0.00396 | $0.00396 |
| Sonnet 5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
agenttape 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype Instructions
AgentTape is now a Codex plugin first. Phase 1 is a repository-local installable plugin that records supported Codex hook events, marks explicit tool failures, and emits a redacted version 1 .tape artifact. Keep the .tape format and recorder logic independent from the React prototype so later MCP and CI surfaces can reuse them.
The plugin lives under plugins/agenttape/ and the repo marketplace entry lives at .agents/plugins/marketplace.json. Treat hooks/hooks.json, the bundled recorder scripts, and the capture skill as the Phase 1 product surface. Do not claim bit-exact or complete replay: Codex hosted tools are outside local hook coverage.
Run the local server yourself and open the preview in the browser available to this environment. Do not give the user server-start instructions when you can run it.
Before making substantial visual changes, use the Product Design plugin's get-context skill when the visual source is unclear or no longer matches the current goal. When the user gives durable prototype-specific design feedback, preferences, or decisions, record them in AGENTS.md.
When implementing from a selected generated mock, treat that image as the source of truth for layout, component anatomy, density, spacing, color, typography, visible content, and hierarchy.
The selected AgentTape direction is option 2: a warm-white desktop causal branch canvas. Preserve the three-pane anatomy (run list, execution graph, evidence inspector), the original-failure versus successful-fork comparison, and the core path from failure injection to a saved .tape regression test.
Build app UI in src/. Keep .openai/hosting.json, worker/index.js, scripts/prepare-sites-build.mjs, and tests/sites-worker.test.mjs intact so the same local prototype can be handed to Sites. Before a Sites handoff, run npm run build and npm run test:sites; the build must leave dist/client/index.html, dist/server/index.js, and dist/.openai/hosting.json.
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 · 28 lines · 793 tokens per session scan A ecebccb2f8ea
agenttape AGENTS.md is an instructions file published in the GitHub repository jiangkoumo/agenttape (1 stars, last pushed 3d ago), licensed MIT. It adds 793 tokens to every session, about $0.0040 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
supergraph AGENTS.md
Instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
project-legibility AGENTS.md
Instructions for perhapsspy/project-legibility, covering agents.md and 검증.
LifeHack-2026 CLAUDE.md
Instructions for Ducksss/LifeHack-2026: Before changing this repository, read AGENTS.md in full and follow its canonical context order, product invariants, worktree rules, and definition of done. Then read docs/HANDOVER.md for the latest product and repository state.
consult CLAUDE.md
Claude Code instructions for kreek/consult, covering claude.md and pi self-improvement source access.
lianhuanhua-skills AGENTS.md
Instructions for littlewindy123/lianhuanhua-skills, covering agents.md, project goal, architecture rules, commands and before committing.
ai-plugin GEMINI.md
Gemini CLI instructions for PostHog/ai-plugin, covering posthog extension, available tool categories and guidelines.