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 Miosa-osa/OSA --skill honeytokens-deceptiongit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/honeytokens-deception)<a href="https://agentmods.dev/skills/miosa-osa/osa/honeytokens-deception"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/honeytokens-deception/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/miosa-osa/osa/honeytokens-deception"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/honeytokens-deception.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00122 | $0.01301 |
| Opus 5.5 | $0.00049 | $0.00520 |
| Sonnet 5.5 | $0.00024 | $0.00260 |
| Haiku 4.5 | $0.00012 | $0.00130 |
Grade A, and why
honeytokens-deception 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 1mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Honeytokens & Deception
Derived from T3MP3ST's src/deception/honeytokens.ts (Apache-2.0). A honeytoken
is a deliberately fake asset whose ONLY purpose is to be used by an attacker —
any use is a high-fidelity intrusion signal.
1. Token kinds and where each belongs
| Kind | Shape | Plant where |
|---|---|---|
opaque |
random 32-byte string | files, DNS TXT-ish records, config comments |
api-key |
provider-shaped key string | source repos, CI configs, docs, S3 buckets |
credential |
username + password pair | database dumps, config files, "leftover" notes |
beacon |
URL/hostname that logs hits | email signatures, PDFs, spreadsheets, DNS |
Placement rule: the token must be reachable by an attacker but not used by anyone legitimate. A honeytoken in active use is noise, not detection.
2. Lifecycle — every state transition is explicit and audited
created → active → (rotated → active) → revoked → cleaned
- created: token generated (32 random bytes, base64url for output), metadata
recorded (
label,kind,environment,generation, timestamps). Not yet armed. - activate: arming is a separate step, and it is AUTHORIZED — deployment is
rejected unless the target environment is in the operator's authorized set.
Only a freshly
createdtoken can be activated (no re-arming revoked tokens). - rotate: revoke + create in one audited action; the replacement inherits
the label/kind/environment and bumps
generation. Rotation keeps the audit trail linked (replaces:<old-id>). - revoke: state flips, the digest index drops the token, and the raw key material is zero-filled. Revocation is idempotent.
- cleanup: removes the token from the store entirely after revocation.
- Every action (
created | activated | rotated | revoked | cleaned | triggered | classified | replay-rejected) lands in an append-only audit log with actor + timestamp.
3. Trigger verification — nonces, signatures, replay protection
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.
- 1mo ago First seen · 114 lines · 122 tokens per session scan A 0c71b664c6d5
honeytokens-deception is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 122 tokens to every session and 1,301 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
unit-converter
Converts between common units of measurement including temperature, distance, and weight.
code-review
Reviews code changes for quality, security, and best practices.
tui-design
This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets…
bun-development
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.
worker-mcp-orchestrator
Guides the coordinator agent on how to orchestrate, delegate to, and supervise local worker agents using the worker-mcp server.
clack
Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.