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/apache/tika/agents-mdgit clone --depth 1 https://github.com/apache/tikaWhat 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 | $0.00936 | $0.00936 |
| Opus 5 | $0.00468 | $0.00468 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
tika 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidance for Apache Tika
Detailed guidance lives in .skills/ — devs/ for working on Tika,
users/ for using it as a tool; one directory per skill, each with a
SKILL.md. Read .skills/devs/development/SKILL.md before doing anything else — it has
the ground rules: build with ./mvnw (always clean, -Pfast for quick
builds), never run git commit/git push or write to GitHub, code and test
conventions, pre-commit checks.
.skills/ is contributor guidance, not project policy (that lives in
SECURITY.md, CONTRIBUTING.md, and the release process).
Local overrides
A skill may have a private companion at $TIKA_SKILLS_LOCAL/<name>/LOCAL.md
(default ~/.tika-skills): machine paths, personal workflow defaults. Read it
after the public skill; it wins on conflict. Additive unless a ## Replaces
section names public rules it turns off. Never committed, never quoted into
any public artifact.
Working on Tika
Contributor-facing — building, testing, and releasing this codebase.
| Skill | Use when |
|---|---|
.skills/devs/development/SKILL.md |
Any development task — load at session start |
.skills/devs/feature-workflow/SKILL.md |
Multi-PR features; reviews keep changing interfaces; splitting a large branch |
.skills/devs/pr-review/SKILL.md |
Reviewing a PR or branch, or self-reviewing before submitting |
.skills/devs/metadata-schema/SKILL.md |
Adding/renaming metadata keys; schema gate failures |
.skills/devs/tika-eval-compare/SKILL.md |
Before/after corpus comparison of two Tika builds |
.skills/devs/tika-eval-encoding-regression/SKILL.md |
Charset-detector regression hunts |
.skills/devs/tika-eval-h2-query/SKILL.md |
Querying the tika-eval H2 database directly |
.skills/devs/update-site-for-release/SKILL.md |
Updating tika.apache.org for a release |
.skills/devs/oss-fuzz/SKILL.md |
Fuzzing a parser locally (OSS-Fuzz Jazzer targets); reproducing an OSS-Fuzz crash |
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.
- yesterday First seen · 74 lines · 936 tokens per session scan A cb7d84170954
tika AGENTS.md is an instructions file published in the GitHub repository apache/tika (4,018 stars, last pushed 2d ago), licensed Apache-2.0. It adds 936 tokens to every session, about $0.0047 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
Cobalt CLAUDE.md
Instructions for Auties00/Cobalt, covering cobalt, build, maven modules, architecture and client hierarchy.
imgui-java CLAUDE.md
Instructions for SpaiR/imgui-java: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
toBeBetterJavaer AGENTS.md
AGENTS.md instructions for itwanger/toBeBetterJavaer, covering 工具权限设置, 工具使用规则, 获取网页内容 and 图片生成 / 文章配图.
Sighthound AGENTS.md
Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.
deptrust AGENTS.md
Instructions for clidey/deptrust, covering what this is, commands, architecture, adding an ecosystem and distribution.
EDDI AGENTS.md
Instructions for labsai/EDDI, covering eddi backend — ai agent instructions, 1. project context, ecosystem, key architecture and build & test commands.