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/chats-is/termory/claude-mdgit clone --depth 1 https://github.com/chats-is/termoryWrote 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/chats-is/termory/claude-md)<a href="https://agentmods.dev/instructions/chats-is/termory/claude-md"><img src="https://agentmods.dev/badge/instructions/chats-is/termory/claude-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 | $0.29193 | $0.29193 |
| Opus 5 | $0.14597 | $0.14597 |
| Sonnet 5 | $0.05839 | $0.05839 |
| Haiku 4.5 | $0.02919 | $0.02919 |
Grade C, and why
termory CLAUDE.md scanned grade C with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **stdin AND stderr are both `Stdio::null()` (LOCKED).** stdin: `opencode upgrade` prompts when it cannot identify the install method and `claude update` can want a sudo password — with no stdin those exit non-zero inst Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| **Claude Code** | `~/.claude/settings.json` (merge): `env.ANTHROPIC_BASE_URL` / `_AUTH_TOKEN` / `_MODEL` + optional sub-routing keys. **Always writes `AUTH_TOKEN` and CLEARS `ANTHROPIC_API_KEY`** — Claude reads AUTH_TO How it starts
The opening of the file, as written. The whole thing — 898 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Scope
Rules for working in this repository — constraints the code cannot tell you, and things that must or must not be done. Implementation detail belongs in the code; history belongs in git.
The app
Tauri v2 + React desktop app. Browses the local history (sessions, memory, skills) that Codex / Claude Code / Gemini CLI / OpenCode / Grok Build store on disk, and switches each tool's API provider. Claude Desktop is provider-switchable too (GUI app, no history). User-facing docs are README.md and docs/GUIDE.md — do not duplicate them here.
Modules are named for what they do (ls src-tauri/src/, ls src/lib/). Rust tests are inline at the bottom of each module. The IPC surface is generate_handler! in lib.rs.
Features spanning several files:
- i18n —
src/i18n/(<I18nProvider>+useT()) - Local store —
src/config.tsroutes over IPC to~/.termory/{config,providers,favorites}.json(Rustconfig.rs) - Multi-account —
accounts.rs+claude_auth.rs+OfficialAccountsSection.tsx - Quota —
quota.rs+useQuotas.ts - Balance —
balance.rs+useBalances.ts+balance-utils.ts - Stats —
stats-utils.ts(pure) +src/components/stats/ - Favorites —
favorites.ts(pure) +src/components/favorites/ - Find (⌘F) —
TranscriptFindBar.tsx+DocDetailView.tsx+highlight-term.ts - Migrate/delete —
sessions.rs(*_infns) +migrate.ts+records.ts
Security boundary — the frontend never sends a path (LOCKED)
A filesystem path is never accepted as an IPC argument. The frontend sends (source, id) or (project, rel); the backend resolves the real path itself and refuses anything outside what it already knows.
load_sessionlooks the path up inSESSION_PATH_INDEXand refuses anything that was not part of the most recent scan, so a path the renderer does not know about cannot reachparse_doc_file/parse_codex_sessionat all. This inverts an earlier design where the path came from the frontend and was validated against an allow-list — do not go back to it.- Migrate and delete take
(project, rel)or an id and build the path under a bounded root, guarded byis_safe_rel(every component Normal; rejects..and absolute). - The session id is charset-guarded (
[A-Za-z0-9._-]) before it is interpolated into a resume command — injection defence.
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 · 898 lines · 29,193 tokens per session scan C d147d9c2eeba
termory CLAUDE.md is an instructions file published in the GitHub repository chats-is/termory (23 stars, last pushed 10d ago), licensed MIT. It adds 29,193 tokens to every session, about $0.1460 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). 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.