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/observability-oss/progress-observability-plugin/copilot-instructionsgit clone --depth 1 https://github.com/observability-oss/progress-observability-pluginWhat 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 | $0.10542 | $0.10542 |
| Opus 5 | $0.05271 | $0.05271 |
| Sonnet 5 | $0.02108 | $0.02108 |
| Haiku 4.5 | $0.01054 | $0.01054 |
Grade E, and why
progress-observability-plugin copilot-instructions.md scanned grade E with 3 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 yesterday.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- GENERATED FILE — do not edit .github/copilot-instructions.md by hand. Regenerate: python scripts/build_copilot.py Sources: references/mcp.md, skills/*/SKILL.md, skills/generate-eval/references/frame.md CI check: pyt Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <target-folder>/.git Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://mcp.observability.progress.com/mcp \ How it starts
The opening of the file, as written. The whole thing — 800 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions: Progress Observability
This file is generated from the plugin's skills. Do not edit it directly — edit the sources and run
python scripts/build_copilot.py. If anything here conflicts with what the user asks for, the user's request wins.
This project works with the Progress Observability Platform over the
progress-observability MCP server. Seven skills are available — pick the one
that matches the request (each also has a matching /prompt):
- instrument-agent — retrofit instrumentation onto an existing Python, TypeScript, or .NET agent, then hand off to health-check to confirm traces arrive. Start here: nothing else has anything to read until traces are flowing.
- scaffold-agent — create a new .NET agent project, already instrumented, from the starter template.
- health-check — verify the setup is wired up: connection, key scope, data flow, instrumentation depth. Run first when something looks wrong.
- trace-triage — root-cause a failed or slow run by walking its span tree.
- cost-report — spend by model/app/day, quota burn, spike explanation.
- coverage-gaps — find production behaviors with no eval; rank what to build.
- generate-eval — build a research-grounded LLM-as-a-Judge evaluator prompt.
Five of the seven only read from the MCP server and write nothing. The two that
write code: scaffold-agent creates a new project and makes no MCP calls;
instrument-agent edits an existing one and reads MCP only to verify.
MCP contract (applies to every workflow)
Endpoint: https://mcp.observability.progress.com/mcp — remote, read-only.
Auth: X-Api-Key header (the plugin's .mcp.json supplies it from
OBSERVABILITY_MCP_API_KEY). Access is scoped by key.
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.
- yesterday First seen · 800 lines · 10,542 tokens per session scan E 9fb1c346b563
progress-observability-plugin copilot-instructions.md is an instructions file published in the GitHub repository observability-oss/progress-observability-plugin (2 stars, last pushed 6d ago), licensed MIT. It adds 10,542 tokens to every session, about $0.0527 per session on Opus 5. A static security scan graded it E with 3 findings (hidden instructions, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.