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 skills add tushaarmehtaa/tushar-skills --skill agent-instructionsgit clone --depth 1 https://github.com/tushaarmehtaa/tushar-skillsWrote 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/skills/tushaarmehtaa/tushar-skills/agent-instructions)<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/agent-instructions"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/agent-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tushaarmehtaa/tushar-skills/agent-instructions"><img src="https://agentmods.dev/badge/skills/tushaarmehtaa/tushar-skills/agent-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.02138 |
| Opus 5.5 | $0.00018 | $0.00855 |
| Sonnet 5.5 | $0.00009 | $0.00428 |
| Haiku 4.5 | $0.00005 | $0.00214 |
Grade B, and why
agent-instructions scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Codex fallback names.** Read `project_doc_fallback_filenames` and `project_doc_max_bytes` in `~/.codex/config.toml` (or `$CODEX_HOME`) when present. A fallback-named file is an instruction file for Codex. How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Write the smallest set of instruction files that each target runtime actually loads. A correct file in a location the runtime skips, or one shadowed by another file, does nothing. Recover facts from the repository before asking, and separate commands you ran from commands you only read about.
Choose the task
- Create: no instruction files exist.
- Improve: one existing file is thin, stale or bloated.
- Reconcile: files duplicate or contradict each other, or one runtime ignores guidance the others see.
- Scope a subtree: a package or directory needs different commands, ownership or boundaries.
- Explain loading: the user asks why an agent ignores its instructions. Report what each runtime loads here. Change nothing unless asked.
Infer the target runtimes from the request, existing files and the user's tooling. Ask only when the answer changes which files exist. "Make this work for our agents" with no other signal means Claude Code, Codex and Cursor.
Read the loading matrix first
Read the loading matrix before choosing any file. It records which files Claude Code, Codex and Cursor read, in what order, with which limits, checked on a stated date. Follow its run-time rule: re-check a runtime's docs when the check date is more than about 90 days old or the installed runtime is older than a version it names.
Inventory every instruction source
pwd
git rev-parse --show-toplevel
rg --files --hidden -g '!node_modules' -g '!.git' \
-g '**/AGENTS.md' -g '**/AGENTS.override.md' -g '**/CLAUDE.md' -g '**/CLAUDE.local.md' \
-g '**/.claude/rules/**' -g '**/.cursor/rules/**' -g '**/.cursorrules'
Then check three places rg misses:
- Ancestors above the repository root. Claude Code loads every
CLAUDE.md,.claude/CLAUDE.mdandCLAUDE.local.mdfrom cwd upward. One in a parent folder shadows the repository'sAGENTS.mdfor Claude Code. Ignore~/.claude/CLAUDE.md; it does not shadow. - Codex fallback names. Read
project_doc_fallback_filenamesandproject_doc_max_bytesin~/.codex/config.toml(or$CODEX_HOME) when present. A fallback-named file is an instruction file for Codex. - Fixture and example directories. An
AGENTS.mdorCLAUDE.mdinside test fixtures, examples or proof folders loads as a real instruction for Claude Code and Cursor when work touches that folder.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +7 lines · +6 tokens per session scan A → B 37f04e78b33f
- 2mo ago First seen · 120 lines · 39 tokens per session scan A d4ef3f990984
agent-instructions is a skill published in the GitHub repository tushaarmehtaa/tushar-skills (12 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 2,138 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
agent-instructions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-instructionstushaarmehtaa/tushar-skills | Skill | 12 | 2d ago | MIT | B | 45 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |