agent-trace AGENTS.md

Repository instructions that tell coding agents how to work on the agent-strace Python project, including its layout, rules, tests, documentation, and installation.

In plain words
What is it for?
Use them when modifying agent-strace, adding commands or features, updating tests and documentation, or installing the project for development.
Why use it?
They give an agent the project’s constraints before it changes code, reducing mistakes such as breaking stored session data or adding required packages incorrectly.

Instructions file for CodexOpenCode

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/siddhant-k-code/agent-trace/agents-md
Clone the repo
git clone --depth 1 https://github.com/Siddhant-K-code/agent-trace

Made for: Codex, OpenCode.

Per session 896 This file is loaded in full into every session.
When invoked 896 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.

ModelPer sessionOnce invoked
Fable 5 $0.00896 $0.00896
Opus 5 $0.00448 $0.00448
Sonnet 5 $0.00179 $0.00179
Haiku 4.5 $0.00090 $0.00090

Measured 2d ago against content hash 09f06df030c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-trace 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — agent-strace development guide

This file tells AI coding agents how to work with the agent-strace repository.

Project layout

src/agent_trace/    Core library — one module per feature
tests/              One test file per module (test_<module>.py)
ADRs/               Architecture Decision Records — read before adding dependencies
docs/               User-facing documentation (setup, commands, production, integrations, security)
examples/           Usage examples for each integration
pyproject.toml      Package config and optional extras

Constraints

  • Zero runtime dependencies in src/agent_trace/. Use Python stdlib only. If a feature requires a third-party package, it must be an optional extra in pyproject.toml under [project.optional-dependencies], imported lazily inside the function with a clear ImportError message. See ADR-0003.
  • Never change the .agent-traces/ storage format in a way that breaks existing sessions. Adding new fields is fine. Removing or renaming existing fields requires a major version bump and human approval.
  • Every new CLI command must be registered in cli.py following the existing subparser pattern.
  • Every new feature must have tests in tests/test_<module>.py. Run python -m unittest discover -s tests -v to verify.
  • OTLP export uses HTTP/JSON only — no gRPC. See ADR-0006.

Development workflow

# Install in editable mode
pip install -e .

# Run tests
python -m unittest discover -s tests -v

# Run a single test file
python -m unittest discover -s tests -p 'test_watch.py' -v

Adding a new feature

  1. Create src/agent_trace/<feature>.py
  2. Add a cmd_<feature> function following the pattern in existing modules
  3. Import and register it in cli.py
  4. Add new EventType values to models.py if needed
  5. Write tests in tests/test_<feature>.py
  6. Add the command to the appropriate table in README.md (one line, linked to docs/)
  7. Add full flag reference to docs/commands.md
  8. If the feature involves production export, update docs/production.md
  9. If the feature involves a new integration, update docs/integrations.md

Read the full file on GitHub · 81 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.

  1. 2d ago First seen · 81 lines · 896 tokens per session scan A 09f06df030c2

Subscribe to this mod's changes

agent-trace AGENTS.md is an instructions file published in the GitHub repository Siddhant-K-code/agent-trace (90 stars, last pushed 10d ago), licensed MIT. It adds 896 tokens to every session, about $0.0045 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.