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/tyql688/sessionview/agents-mdgit clone --depth 1 https://github.com/tyql688/sessionviewWhat 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 | $0.02099 | $0.02099 |
| Opus 5 | $0.01050 | $0.01050 |
| Sonnet 5 | $0.00420 | $0.00420 |
| Haiku 4.5 | $0.00210 | $0.00210 |
Grade A, and why
sessionview 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SessionView
Guidance for Claude Code (claude.ai/code) and other agents working in this repository. CLAUDE.md includes this file via @AGENTS.md.
SessionView is a desktop app that brings local AI coding sessions from many tools — Claude Code, Codex, Antigravity, Kimi Code, Cursor, OpenCode, CC-Mirror, Pi, Grok Build, and DSH (DeepSeek Harness) — into one place to read, search, analyze usage, export, and resume.
Stack: Tauri 2 + React 19 (with React Compiler) + Rust + SQLite (FTS5).
Enforcement-mapped coding standards live in style/ts.md and style/rust.md; when this file and those disagree, those win.
Commands
# App / frontend
npm run tauri dev # run the app with hot reload
npm run tauri build # production bundle
# Headless server (browser shell; build dist first so it can be embedded)
npm run build && cd src-tauri && \
cargo build --release --no-default-features --features headless
# gates must pass under BOTH feature sets: default (gui) and
# --no-default-features --features headless
npm run check # typecheck + Biome + ESLint — the frontend gate
npm test # frontend tests (Vitest, run mode)
npm run knip # dead-code / dependency audit — a release gate
# Rust backend (run from src-tauri/)
cargo test # backend tests
cargo fmt --check # format check
cargo clippy --all-targets --all-features -- -D warnings # lint, CI-strict
# Release
./scripts/release.sh <version> # bump, commit, tag, push -> CI release
Run a single test:
npm test -- src/lib/foo.test.ts # one frontend file
npx vitest run -t "resolves subagent" # frontend, by test name
cd src-tauri && cargo test parent_backfills # one Rust test by name substring
cd src-tauri && cargo test --test parser_tests# one Rust integration-test file
Real-data smoke tests (src-tauri/tests/*_real_*.rs) are #[ignore] by default; run them explicitly with cargo test -- --ignored. Git hooks (lefthook) pre-commit format staged frontend files and run ESLint; pre-push runs npm run check + npm test and the Rust fmt/clippy/test gate. CI and scripts/release.sh are the source of truth for exact commands.
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 · 75 lines · 2,099 tokens per session scan A 6b32a1613d32
sessionview AGENTS.md is an instructions file published in the GitHub repository tyql688/sessionview (15 stars, last pushed 14d ago), licensed MIT. It adds 2,099 tokens to every session, about $0.0105 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
hapi AGENTS.md
AGENTS.md instructions for tiann/hapi, covering agents.md, what is hapi?, repo layout, architecture overview and reference docs.
open-vibe-island AGENTS.md
AGENTS.md instructions for Octane0411/open-vibe-island, covering agents, goal, required workflow, commit policy and safety rules.
open-vibe-island CLAUDE.md
Claude Code instructions for Octane0411/open-vibe-island, covering claude.md, project, architecture, build & run and dev app (open island dev.app).
libtmux-mcp AGENTS.md
Instructions for tmux-python/libtmux-mcp, covering agents.md, what is here, which policy applies, change discipline and references.
wingman AGENTS.md
Instructions for eat-pray-ai/wingman, covering agents.md — wingman (@eat-pray-ai/wingman), quick reference and documentation index.
agent-exporter AGENTS.md
Instructions for ihatenodejs/agent-exporter, covering development commands, example: bun run dev sync --provider opencode, creates compiled binary at dist/agent-exporter, then use: agent-exporter and architecture.