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/tardigrde/obsidian-agentic-chat/agents-mdgit clone --depth 1 https://github.com/tardigrde/obsidian-agentic-chatWrote 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/tardigrde/obsidian-agentic-chat/agents-md)<a href="https://agentmods.dev/instructions/tardigrde/obsidian-agentic-chat/agents-md"><img src="https://agentmods.dev/badge/instructions/tardigrde/obsidian-agentic-chat/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 | $0.01485 | $0.01485 |
| Opus 5 | $0.00743 | $0.00743 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
obsidian-agentic-chat 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 5d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Fast Feedback Loop
Use ~/MyTestVault as the local dogfood vault unless the user names another vault.
Install the current built plugin into a vault:
npm run install:local -- ~/MyTestVault
Run the fastest Obsidian development loop:
npm run dev:vault -- ~/MyTestVault
dev:vault installs real plugin files under
~/MyTestVault/.obsidian/plugins/agentic-chat/, creates .hotreload, and writes esbuild output directly to that plugin directory. For automatic JS reloads inside Obsidian, install and enable pjeby/hot-reload in the same vault. If hot reload is unavailable, reload manually from Obsidian DevTools:
await app.plugins.disablePlugin("agentic-chat");
await app.plugins.enablePlugin("agentic-chat");
Use the one-command dogfood loop when actively stabilizing:
npm run dogfood -- ~/MyTestVault
dogfood enables the local plugin in the vault, enables any installed hot-reload
plugin whose manifest matches "hot reload", starts the direct-to-vault esbuild
watcher, opens the vault through Obsidian's URI handler when available, and
tails local session JSONL plus e2e artifact text/JSON. Use --once --no-open --no-tail for a non-interactive build/install check.
Run local verification in this order while iterating:
npm run verify:fast
That command expands to:
npm run typecheck
npm run lint
npm test
npm run test:e2e -- --spec test/e2e/specs/smoke.e2e.ts
npm run test:e2e uses scripts/run-e2e.ts: it resolves the matching
obsidian-launcher chromedriver, starts it on a fixed low localhost port
(9515-9520), and points WDIO at it with WDIO_SKIP_DRIVER_SETUP=1. This
avoids WSL/proxy failures where WDIO's random high chromedriver port exits with
bind() failed: Address already in use / IPv6 port not available. To run the
full local suite without spending tokens, clear the live key so the model-backed
guardrail spec skips:
AGENTIC_CHAT_API_KEY= npm run test:e2e
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.
- 5d ago First seen · 156 lines · 1,485 tokens per session scan A e53a03543488
obsidian-agentic-chat AGENTS.md is an instructions file published in the GitHub repository tardigrde/obsidian-agentic-chat (5 stars, last pushed today), licensed MIT. It adds 1,485 tokens to every session, about $0.0074 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
WuKongIM AGENTS.md
AGENTS.md instructions for WuKongIM/WuKongIM, covering agents.md, project and rule levels, core runtime semantics, before you work and design and implementation.
chat.md CLAUDE.md
Instructions for rusiaaman/chat.md, covering what is the extension about?, theory, states, .chat.md parsing and %% system.
workbuddian CLAUDE.md
Instructions for jiang198012/workbuddian, covering claude.md, what this is, commands, build & distribution model and architecture.
piclaw-addons AGENTS.md
AGENTS.md instructions for rcarmo/piclaw-addons, covering developing piclaw add-ons, quick start, 1. create your addon directory, 2. write your entry point, package.json, and skill and 3. sync the catalog.
agent-skills AGENTS.md
AGENTS.md instructions for GetStream/agent-skills, covering agents.md - codex entrypoint for the stream skill pack, sub-skills, codex-specific and install.
Arkloop AGENTS.md
AGENTS.md instructions for qqqqqf-q/Arkloop, covering arkloop, architecture, backend services, backend workflow and 构建与测试(单一构建模式,无 build tag).