What is opensre AGENTS.md?

A set of development instructions for Tracer-Cloud and OpenSRE projects, covering code conventions, tests, builds, and continuous-integration checks. Continuous integration means automatically building and testing changes after they are pushed.

Use it when developing, reviewing, or pushing changes, especially when running focused tests, checking imports, inspecting CI logs, and monitoring pull-request checks.

It helps agents follow the repository's rules and close the loop when tests or required checks fail.

opensre AGENTS.md — Instructions file by Tracer-Cloud

Install

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.

agentmods

npx agentmods add instructions/tracer-cloud/opensre/agents-md

Clone the repo

git clone --depth 1 https://github.com/Tracer-Cloud/opensre

Made for: Codex, OpenCode.

Per session 7,397 This file is loaded in full into every session.

When invoked 7,397 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.07397	$0.07397
Opus 5	$0.03698	$0.03698
Sonnet 5	$0.01479	$0.01479
Haiku 4.5	$0.00740	$0.00740

Measured 2d ago against content hash f8f585346f27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opensre 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 2d 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.

AGENTS.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSRE Development Reference

CI failures and tests (mandatory — every PR / push)

Agents must close the loop on CI and tests. Do not treat "pushed a fix" or "opened a PR" as done.

After every push to a branch with an open PR, run:

gh pr checks --watch
# or: gh pr view --json statusCheckRollup,url

On any failure (CI Gate, quality, test (*), import graph, etc.):
- Pull the failing job log (gh run view <id> --log-failed).
- Fix the root cause in product or test code (not by skipping / constant-condition toggles).
- Re-run the focused local commands from CI.md for the touched modules, then push.
- Re-check gh pr checks until required jobs are green (or skipped for docs-only).
Tests that fail under CI load (xdist, barriers, fan-out concurrency) are real bugs in the test harness — harden synchronization; do not ignore flakes.
Import / API-border failures (check_imports.py, test_integrations_api_border) mean the wrong module edge was used — import the package API allowlisted in .importlinter.strict / the border allowlist, not an internal leaf, unless the ignore list explicitly names that edge.
Keep monitoring until merge requirements in CI.md §8 (green checks + Greptile 5/5) are met.
After merge, monitor the merge commit's main CI, full CodeQL, and release workflows. A post-merge failure is unfinished delivery: fix or revert it before reporting completion.

The Cursor project hook .cursor/hooks/check-ci-failures.sh (wired in .cursor/hooks.json) re-injects this checklist on agent stop when the current branch's PR has failing checks — treat that follow-up as blocking work, not a suggestion.

Build and Run commands

Build make install (sets up the project environment via uv sync and installs this repo in editable mode)
Run uv run opensre … from the repo root while developing — preferred approach, uses this checkout even if another opensre is on your PATH.
Use uv run python … for any Python commands.

Read the full file on GitHub · 378 lines

Changes

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.

2d ago First seen · 378 lines · 7,397 tokens per session scan A f8f585346f27

Subscribe to this mod's changes

opensre AGENTS.md is an instructions file published in the GitHub repository Tracer-Cloud/opensre (10,985 stars, last pushed today), licensed Apache-2.0. It adds 7,397 tokens to every session, about $0.0370 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.

ai-sre alerting datadog grafana observability remediation

opensre AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

OpenSRE Development Reference

CI failures and tests (mandatory — every PR / push)

Build and Run commands

What this file has done since we first saw it

Other instructions, from other repositories

ongrid AGENTS.md

pup CLAUDE.md

mcp-read-only-grafana CLAUDE.md

mcp-read-only-grafana AGENTS.md

pup AGENTS.md

llm-cli-telemetry CLAUDE.md