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/creght-dev/skills/agents-mdgit clone --depth 1 https://github.com/creght-dev/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/instructions/creght-dev/skills/agents-md)<a href="https://agentmods.dev/instructions/creght-dev/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/creght-dev/skills/agents-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 | $0.00846 | $0.00846 |
| Opus 5 | $0.00423 | $0.00423 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
skills 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 4d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — how the Creght / Talizen skills relate
This repo holds the external Creght skill. It is one of three sibling agent-skills for the same platform; they share most guidance but target different audiences and must be kept consistent. Read this before editing.
The three skills
| Skill | Location | Audience | Tooling model |
|---|---|---|---|
| talizen-system | talizen-system/ in the talizen/skills repo |
The in-platform agent that runs inside the Talizen / Creght editor | Has platform tools: lint, create_version, diff_patch_file, fetch_module_types, import-map, preview. No CLI workflow. |
| talizen (external) | skills/talizen/ in the talizen/skills repo |
End users / general-purpose agents working locally via the Talizen CLI | CLI workflow (pull / push / watch / preview). Platform tools only "if the environment exposes them, otherwise use the CLI". |
| creght (external) | skills/creght/ (this repo) |
End users of Creght | Same as external talizen, but Creght-branded. |
- Creght integrates Talizen's capabilities, and Talizen is also operated as an independent platform. Creght and Talizen therefore share the same code model and SDK — the only differences are the platform name and branding.
talizen-systemis the source of truth. It is the newest and most complete. This external Creght skill is downstream and is kept in sync with its audience-neutral content, then rebranded (see below).
Syncing content from talizen-system → this skill
Do not blind-copy. When porting guidance from talizen-system:
- Filenames — all three skills use lowercase kebab-case under
references/(cms.md,forms.md,error-handling.md,site-code.md);SKILL.mdlinks files by name, so keep this consistent across the three. - Keep external-only files —
cli.mdandsite-code.mdexist only in the external skills (they document the CLI / local workflow).talizen-systemhas no equivalent; never delete them during a sync. - Filter platform-only content — strip or rewrite anything that assumes the
in-platform agent: the
lint/create_version/diff_patch_file/fetch_module_types/create_collection/ import-map tools, and theLINT_ERROR/BROWSER_ERROR_RENDERevents plus preview-runtime specifics. Those events are delivered only to the in-platform agent — a local CLI agent never receives them, so external docs must not wait for or trigger on them. Re-express as CLI / general guidance, or drop it. error-handlingis intentionally its own document —talizen-systemkeeps a platform/preview version (BROWSER_ERROR_RENDER, preview-runtime, the built-in React runtime). This skill carries a CLI-oriented version. Keep them separate; do not merge them back into one.
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.
- 4d ago First seen · 52 lines · 846 tokens per session scan A eb9c3841bc3b
skills AGENTS.md is an instructions file published in the GitHub repository creght-dev/skills (10 stars, last pushed yesterday), licensed MIT. It adds 846 tokens to every session, about $0.0042 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.
Other instructions, from other repositories
EchoBird AGENTS.md
AGENTS.md instructions for edison7009/EchoBird, covering agents.md — echobird, project shape, ci gates (must pass locally before pushing), lesson (learned the hard way) and verification habits.
Agentkey AGENTS.md
Instructions for chainbase-labs/Agentkey, covering agents.md, what this repo is, directory structure, key commands and test a local edit against every detected agent.
superdesign-skill AGENTS.md
Instructions for superdesigndev/superdesign-skill, covering project agent memory, what this repo is, skill flow invariant: two entry paths, ground truth for cli behavior and plugin packaging & release.
seektty AGENTS.md
AGENTS.md instructions for Hilbert-beinghappy/seektty: This repository ships one out-of-tree DeepSeek Harness Bundle. Harness remains the only owner of Agent, Session, model, settings, permissions, Profile, plugin, and persistence state.
causal-memory CLAUDE.md
Claude Code instructions for JingxuanC/causal-memory, covering causal memory mcp integration, causal memory integration, after acting on a decision and observing the result, when something fails unexpectedly and when a recorded lesson turns out to be wrong.
dsh-deepread AGENTS.md
AGENTS.md instructions for xiehuan123/dsh-deepread, covering agents.md, upstream authority, plugin identities and source files, release documentation and harness lifecycle rules.