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/siddhant-k-code/agent-trace/agents-mdgit clone --depth 1 https://github.com/Siddhant-K-code/agent-traceWhat 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 | $0.00896 | $0.00896 |
| Opus 5 | $0.00448 | $0.00448 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00090 | $0.00090 |
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.
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 inpyproject.tomlunder[project.optional-dependencies], imported lazily inside the function with a clearImportErrormessage. 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.pyfollowing the existing subparser pattern. - Every new feature must have tests in
tests/test_<module>.py. Runpython -m unittest discover -s tests -vto 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
- Create
src/agent_trace/<feature>.py - Add a
cmd_<feature>function following the pattern in existing modules - Import and register it in
cli.py - Add new
EventTypevalues tomodels.pyif needed - Write tests in
tests/test_<feature>.py - Add the command to the appropriate table in
README.md(one line, linked to docs/) - Add full flag reference to
docs/commands.md - If the feature involves production export, update
docs/production.md - If the feature involves a new integration, update
docs/integrations.md
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 · 81 lines · 896 tokens per session scan A 09f06df030c2
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.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.