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/tarampampam/microcheck/agents-mdgit clone --depth 1 https://github.com/tarampampam/microcheckWhat 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 | $0.01234 | $0.01234 |
| Opus 5 | $0.00617 | $0.00617 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
microcheck 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS - Project Rules
Read this file AND the global rules before making any code changes - https://tarampampam.github.io/.github/ai/AGENTS.md (mirror - https://raw.githubusercontent.com/tarampampam/.github/refs/heads/master/ai/AGENTS.md).
Instruction Priority
- This file (
AGENTS.mdin this repository) - Global rules (external URLs)
- Other documentation
If rules conflict, follow the highest priority source.
Build & Test Commands
Requires musl-gcc, make, cmake, python3. Compile sources on any changes to ensure no warnings or errors.
Run all tests after batching changes to ensure no regressions.
make # build all binaries → build/bin/{httpcheck,httpscheck,portcheck,parallel,pidcheck}
make test # build + run all unit tests (C) + all feature tests (Python)
make fmt # format all C source with clang-format
make clean # remove build/ and apps/version.h
APP_VERSION=1.2.3 make # set version string (generates apps/version.h)
Run a single unit test binary:
make build/bin/cli_test && ./build/bin/cli_test # CLI module unit tests
make build/bin/http_test && ./build/bin/http_test # HTTP module unit tests
make build/bin/command_test && ./build/bin/command_test # command parsing unit tests
Run a single feature test suite:
python3 ./tests/feature/httpcheck.py --bin ./build/bin/httpcheck # HTTP mode
python3 ./tests/feature/httpcheck.py --bin ./build/bin/httpscheck --https # HTTPS mode (needs openssl)
python3 ./tests/feature/httpcheck.py --bin ./build/bin/httpscheck --fallback # fallback mode (HTTPS->HTTP)
python3 ./tests/feature/portcheck.py --bin ./build/bin/portcheck
python3 ./tests/feature/parallel.py --bin ./build/bin/parallel
python3 ./tests/feature/pidcheck.py --bin ./build/bin/pidcheck
Architecture
Single-source dual-binary pattern
apps/httpcheck.c compiles to both httpcheck and httpscheck. The difference: httpscheck is compiled with
-DWITH_TLS and linked against mbedTLS 4. All TLS code paths in the file are gated on #ifdef WITH_TLS. Both
binaries share the same CLI flags.
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 · 103 lines · 1,234 tokens per session scan A 90f100d7535d
microcheck AGENTS.md is an instructions file published in the GitHub repository tarampampam/microcheck (151 stars, last pushed 2mo ago), licensed MIT. It adds 1,234 tokens to every session, about $0.0062 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
penpot-aio AGENTS.md
AGENTS.md instructions for JSONbored/penpot-aio, covering agents.md, intent, source of truth, runtime contract and validation.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, mandatory development principles and sow system.
IoTSharp AGENTS.md
Instructions for IoTSharp/IoTSharp, covering agents.md, current mission, current priority order, current concept realignment and ai workbench direction.
IoTSharp copilot-instructions.md
Instructions for IoTSharp/IoTSharp, covering copilot instructions and 项目指南.
selfhost-ai CLAUDE.md
Instructions for kossakovsky/selfhost-ai, covering claude.md, project overview, core architecture, key files and installation flow.