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/qiaolei81/copilot-session-viewer/agents-mdgit clone --depth 1 https://github.com/qiaolei81/copilot-session-viewerWrote 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/qiaolei81/copilot-session-viewer/agents-md)<a href="https://agentmods.dev/instructions/qiaolei81/copilot-session-viewer/agents-md"><img src="https://agentmods.dev/badge/instructions/qiaolei81/copilot-session-viewer/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 5.1 | $0.01474 | $0.01474 |
| Opus 5 | $0.00737 | $0.00737 |
| Sonnet 5 | $0.00295 | $0.00295 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
copilot-session-viewer 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project overview
Web UI for viewing and analyzing AI coding-agent session logs (GitHub Copilot CLI, Claude Code, Pi-Mono, VSCode, Modernize). Built with Express.js backend and a Vue 3 SPA frontend (Vite + Pinia + Vue Router).
Setup commands
- Install deps:
npm install - Start server:
npm start - Dev mode (auto-reload):
npm run dev - Run all tests:
npm run test:all - Lint code:
npm run lint - Fix lint issues:
npm run lint:fix
Code style
- JavaScript (Node.js 22+)
- Single quotes for strings
- No unused variables (prefix with
_if intentionally unused in catch blocks) - Error handling: always include
{ cause }when re-throwing errors - ESLint enforced (no errors, warnings acceptable)
File structure
server.js # Entry: telemetry init + app.listen
src/
server/
app.js # Express app factory (middleware, routes)
config.js # Configuration constants
telemetry.js # App Insights init (must load first)
controllers/ # Route handlers (session, dir, tag, insight, upload, ...)
middleware/ # Express middleware (rate limit, validation, ...)
services/ # sessionService, sessionRepository, insightService,
# eventNormalizer, dirRegistryService, tagService, ...
adapters/ # Per-source session adapters (Copilot, Claude, Pi-Mono,
# VSCode, Modernize) — extend BaseSourceAdapter
models/ # Session domain model
schemas/ # Zod schemas (unified event schema)
utils/ # fileUtils, helpers, processManager, sourceMapping
client/ # Vue 3 SPA (built by Vite, served from dist/client)
main.js, App.vue
router/ # Vue Router (hash mode)
stores/ # Pinia stores
api/ # fetch wrappers
views/ # Route-level views (HomeView, SessionView, TimeAnalyzeView)
components/ # Reusable components (home/, session/, time-analyze/)
utils/, styles/
lib/parsers/ # Legacy parser stack used by ClaudeAdapter via ParserFactory
__tests__/ # Jest unit tests
__tests__/e2e/ # Playwright e2e tests
__tests__/fixtures/sessions/ # Synthetic CLI-generated session fixtures (E2E_USE_FIXTURES=1)
public/ # Static assets served by Express
dist/ # Vite build output (client/) + bundled server.min.js
index.html # Vite entry HTML
vite.config.js # Vite config (Vue plugin, build targets)
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 · 128 lines · 1,474 tokens per session scan A b23fc289ba1f
copilot-session-viewer AGENTS.md is an instructions file published in the GitHub repository qiaolei81/copilot-session-viewer (11 stars, last pushed 5d ago), licensed MIT. It adds 1,474 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 2026-08-30.
Other instructions, from other repositories
github-copilot markdown.instructions.md
Instructions for AB-Lindex/github-copilot: Create clean and professional markdown files.
gortex CLAUDE.md
Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
squad copilot-instructions.md
Copilot instructions for bradygaster/squad, covering copilot coding agent — squad instructions, ⚠️ identity lock — read this first, 🚦 route before you act — generic copilot sessions, adversarial input handling and team context.
vscode-unify-chat-provider AGENTS.md
Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…
calva-backseat-driver AGENTS.md
Instructions for BetterThanTomorrow/calva-backseat-driver, covering calva backseat driver - ai agent guide, essential architecture, action/effect system ("ex"), runtime state structure and datascript connections.
apex-accelerator agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.