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/jessemaxh/glanceterm/claude-mdgit clone --depth 1 https://github.com/jessemaxh/GlanceTermWrote 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/jessemaxh/glanceterm/claude-md)<a href="https://agentmods.dev/instructions/jessemaxh/glanceterm/claude-md"><img src="https://agentmods.dev/badge/instructions/jessemaxh/glanceterm/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 | $0.00685 | $0.00685 |
| Opus 5 | $0.00342 | $0.00342 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
GlanceTerm CLAUDE.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 3d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GlanceTerm — agent rules
Packaging the macOS .dmg
The only correct command is npm run dmg:mac (= node scripts/build-macos.mjs).
It runs the build, prepackages plugins, refreshes app/node_modules via yarn,
and ensures the app/node_modules/electron → ../../node_modules/electron
symlink — all four steps are load-bearing.
Release vs dev version. A plain npm run dmg:mac stamps a traceable dev
version 0.1.0-dev.g<hash>[.dirty] (into the filename AND CFBundleVersion/Short).
For an actual release artifact with a clean 0.1.0, set RELEASE=1:
RELEASE=1 npm run dmg:mac (a signed build without RELEASE=1 prints a warning).
Do not
- Do not call
electron-builderdirectly. It silently ships anapp.asarwith zeronode_modules; the resulting.appcrashes at launch withCannot find module 'v8-compile-cache'. The build "succeeds" so the failure isn't caught until a human runs the app. - Do not set
SKIP_PREPACKAGE=1for a final/ship build. It is for inner-loop iteration on the Electron shell only. Even with a validapp/node_modules/electronsymlink and a fresh(cd app && yarn), the dep walker has been observed to silently bail and ship an asar with zeronode_modules. The unconditional prepackage path is the only one verified to produce a runnable .app. - Do not "save time" by reusing a previous
dist/mac-arm64/build. If you didn't watch thisnpm run dmg:macfinish in this session, treat the artifacts as suspect and rebuild.
Self-check
scripts/build-macos.mjs verifies the asar contains v8-compile-cache,
keytar, source-map-support, and electron-updater inside its
afterPack hook — i.e. before the DMG is assembled. If you see
✖ BROKEN BUILD — app.asar is missing production node_modules, do not
retry blindly: re-read the diagnostic, then run the recommended fix.
Why dist/mac-arm64/GlanceTerm.app gets deleted after the build
npm run dmg:mac removes the loose dist/mac-arm64/GlanceTerm.app once the
DMG/zip are produced (both artifacts already contain it). This avoids
LaunchServices indexing a second GlanceTerm.app next to
/Applications/GlanceTerm.app — when both are registered, Launchpad and
Spotlight return duplicates and can fail to match the app by name. Set
KEEP_DIR_BUILD=1 if you need the unpacked .app for debugging.
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.
- 3d ago First seen · 53 lines · 685 tokens per session scan A 52c90956f02f
GlanceTerm CLAUDE.md is an instructions file published in the GitHub repository jessemaxh/GlanceTerm (1 stars, last pushed 19d ago), licensed MIT. It adds 685 tokens to every session, about $0.0034 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
vscode tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode writing-tests.instructions.md
VS Code test writing guidelines — unit tests, integration tests, snapshot tests, and clean teardown patterns. Reference when writing or updating tests.
vscode interactive.instructions.md
Architecture documentation for VS Code interactive window component. Use when working in src/vs/workbench/contrib/interactive.
vscode notebook.instructions.md
Architecture documentation for VS Code notebook and interactive window components. Use when working in src/vs/workbench/contrib/notebook/.
vscode chat.instructions.md
Chat feature area coding guidelines.