TryCatch AGENTS.md

Repository instructions for working with GitRavz/TryCatch, an audit method whose main deliverable is a skill file and a set of probes. They explain how to audit the repository and how to change its instructions safely.

In plain words
What is it for?
Use them when auditing this repository or modifying its audit method, especially when confirming findings with file paths, line numbers, and exact quotes.
Why use it?
They prevent unverified audit findings and discourage adding rules that make the always-loaded instructions harder to follow. They also account for environments with no network, code execution, or writable files.

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/gitravz/trycatch/agents-md
Clone the repo
git clone --depth 1 https://github.com/GitRavz/TryCatch

Made for: Codex, OpenCode.

Per session 323 This file is loaded in full into every session.
When invoked 323 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 $0.00323 $0.00323
Opus 5 $0.00161 $0.00161
Sonnet 5 $0.00065 $0.00065
Haiku 4.5 $0.00032 $0.00032

Measured yesterday against content hash 6f4e89f598b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TryCatch 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 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.

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 · 27 lines

What it actually says

AGENTS.md

This repository is an audit method. There is no build, no test suite, and nothing to run — the deliverable is SKILL.md plus references/probes.md.

If you were asked to audit something

Read SKILL.md and follow it exactly. The rule that matters most: never report a finding you have not opened the file and confirmed yourself. Search hits and subagent claims are leads. Every finding needs a file, a line number, and a verbatim quote.

If you were asked to modify this repository

  • SKILL.md is loaded into an agent's context on every audit. Every sentence costs attention. Additions must displace something weaker or earn their place.
  • Heavy reference material belongs in references/, which loads only when the method calls for it. Don't move it inline.
  • The rules here are earned from observed failures, not assumed. If you're adding or changing a rule, the commit message should say what real audit behavior prompted it. See CONTRIBUTING.md.
  • Keep the method platform-neutral. It must work in an agent with no subagents, no network, no code execution, and read-only file access. If a change assumes a capability, gate it behind an explicit "if you can…" branch.
  • Don't add framework-specific probes to SKILL.md; they go in references/probes.md under the relevant dimension.
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. yesterday First seen · 27 lines · 323 tokens per session scan A 6f4e89f598b9

Subscribe to this mod's changes

TryCatch AGENTS.md is an instructions file published in the GitHub repository GitRavz/TryCatch (2 stars, last pushed 29d ago), licensed MIT. It adds 323 tokens to every session, about $0.0016 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 2026-08-31.