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/cnighswonger/claude-code-cache-fix/claude-mdgit clone --depth 1 https://github.com/cnighswonger/claude-code-cache-fixWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/cnighswonger/claude-code-cache-fix/claude-md)<a href="https://agentmods.dev/instructions/cnighswonger/claude-code-cache-fix/claude-md"><img src="https://agentmods.dev/badge/instructions/cnighswonger/claude-code-cache-fix/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.03087 | $0.03087 |
| Opus 5 | $0.01543 | $0.01543 |
| Sonnet 5 | $0.00617 | $0.00617 |
| Haiku 4.5 | $0.00309 | $0.00309 |
Grade A, and why
claude-code-cache-fix CLAUDE.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 6d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 6d ago First seen · 134 lines · 3,087 tokens per session scan A 29aa771dfda8
claude-code-cache-fix CLAUDE.md is an instructions file published in the GitHub repository cnighswonger/claude-code-cache-fix (429 stars, last pushed 4d ago), with no licence file. It adds 3,087 tokens to every session, about $0.0154 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
opencode-cache-hit AGENTS.md
AGENTS.md instructions for zhumengzhu/opencode-cache-hit, covering agents.md — maintainer & ai assistant guide, project purpose, documentation map, commands and code conventions.
uwas CLAUDE.md
Claude Code instructions for uwaserver/uwas, covering claude.md, critical directives, project overview, build & test commands and development.
uwas copilot-instructions.md
Copilot instructions for uwaserver/uwas, covering context discipline, tool preferences, session memory and when native tools are acceptable.
uwas AGENTS.md
AGENTS.md instructions for uwaserver/uwas, covering context discipline — required, rule 1 — prefer dfmt tools over native tools, rule 2 — on dfmt failure, report and fall back, rule 3 — record user decisions and why these rules matter.
uwas GEMINI.md
Gemini CLI instructions for uwaserver/uwas, covering context discipline, tool preferences, session memory and when native tools are acceptable.
laravel-agent-mcp copilot-instructions.md
Instructions for anilcancakir/laravel-agent-mcp, covering claude.md, stack, commands, layout (non-obvious) and conventions (project-specific).