Borrowing it
Nothing to install: this file belongs to chats-is/termory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chats-is/termory/main/.claude/skills/run-termory/SKILL.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/skills/chats-is/termory/run-termory)<a href="https://agentmods.dev/skills/chats-is/termory/run-termory"><img src="https://agentmods.dev/badge/skills/chats-is/termory/run-termory/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.
<a href="https://agentmods.dev/skills/chats-is/termory/run-termory"><img src="https://agentmods.dev/badge/skills/chats-is/termory/run-termory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 79 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 100 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 208 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 155 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00064 | $0.03907 |
| Opus 5.5 | $0.00026 | $0.01563 |
| Sonnet 5.5 | $0.00013 | $0.00781 |
| Haiku 4.5 | $0.00006 | $0.00391 |
Grade A, and why
run-termory 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 1mo 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Termory is a native Tauri v2 app (WKWebView) on macOS — not Electron. Drive it
with .claude/skills/run-termory/driver.mjs, which talks to it through macOS
accessibility (osascript) and captures it with screencapture. Paths below are
relative to the repo root.
There is no CDP/DevTools handle. Tauri v2 on macOS exposes no remote-debugging
port, so Playwright's _electron, chromium-cli, and every CDP-based recipe are
dead ends here. Accessibility + screenshots is the whole surface. (xvfb is
likewise irrelevant — this is a real macOS window server, not headless Linux.)
Prerequisites
Already satisfied on this machine; no apt-get/brew step was needed. What must
be true:
- Node (v22.21.1 here) and a Rust toolchain —
npm run tauri:devbuilds both. - Accessibility permission for the terminal app running the driver
(System Settings → Privacy & Security → Accessibility). Without it every
osascriptSystem Events call fails. This was already granted here, so the first-grant prompt is unverified. - Screen Recording permission for
screencapture.
Run (agent path)
node .claude/skills/run-termory/driver.mjs launch # idempotent; prints window bounds
node .claude/skills/run-termory/driver.mjs route 3 # Cmd-1..7 rail: providers/router/records/favorites/search/stats/settings
node .claude/skills/run-termory/driver.mjs search "Wait agent"
node .claude/skills/run-termory/driver.mjs shot /tmp/x.png # look before selecting
node .claude/skills/run-termory/driver.mjs key down down return
node .claude/skills/run-termory/driver.mjs quit
launch spawns npm run tauri:dev detached, logs to /tmp/termory-dev.log, polls
for the process, and fails fast on a compile error instead of sitting out its
15-minute timeout. It then waits out the first session scan (settle, 8s), so
with Rust already built it returns in ~15s (measured); a cold Rust build is
minutes.
Other commands: bounds (window rect as JSON), paste <text> (IME-safe text
entry — see Gotchas), key <spec>… (cmd+k, down, return, esc, …).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed e9383815fd04
- 1mo ago Changed · +3 lines 02c5b0ba3021
- 1mo ago Changed · +54 lines fdb28cd002bd
- 2mo ago First seen · 212 lines · 64 tokens per session scan A 3440dd2b1a3b
run-termory is a skill published in the GitHub repository chats-is/termory (25 stars, last pushed 29d ago), licensed MIT. It adds 64 tokens to every session and 3,907 once invoked, about $0.0003 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 2026-08-30.
run-termory compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| run-termorychats-is/termory | Skill | 25 | 29d ago | MIT | A | 64 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |