Canary Tokens

Canary Tokens is a skill for Claude Code, Codex from TheArchitectit/agent-guardrails-template. It costs 22 tokens per session (772 once invoked), scanned A, original, BSD-3-Clause.

A unique marker placed in a sensitive file so an agent’s output can reveal if that file’s contents were leaked. A detected marker is recorded as a possible data-exfiltration event.

In plain words
What is it for?
Use it to monitor sensitive files such as .env files, key files, secret configurations, private documentation, and other files you identify as confidential.
Why use it?
It helps detect accidental or malicious exposure of credentials, private keys, database settings, or other confidential files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to monitor sensitive files such as .env files, key files, secret configurations, private documentation, and other files you identify as confidential.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thearchitectit/agent-guardrails-template/canary-tokens
Install

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.

Any agent
npx skills add TheArchitectit/agent-guardrails-template --skill canary-tokens
Clone the repo
git clone --depth 1 https://github.com/TheArchitectit/agent-guardrails-template

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Canary Tokens

README.md
[![agentmods](https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/canary-tokens/github.svg)](https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/canary-tokens)
Your own site
<a href="https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/canary-tokens"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/canary-tokens/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.

agentmods 80×15 button for Canary Tokens

Your own site · 80×15
<a href="https://agentmods.dev/skills/thearchitectit/agent-guardrails-template/canary-tokens"><img src="https://agentmods.dev/badge/skills/thearchitectit/agent-guardrails-template/canary-tokens.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 24
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 24
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00772
Opus 5 $0.00011 $0.00386
Sonnet 5 $0.00004 $0.00154
Haiku 4.5 $0.00002 $0.00077

Measured 12d ago against content hash 92dfbfd7404f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Canary Tokens 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 12d 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.

pi-extension/skills/canary-tokens/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Canary Tokens

Canary tokens are unique identifiers inserted into sensitive files. If an agent's output contains a canary token, it indicates potential data exfiltration — the agent has leaked file contents that should have stayed private.

How Canary Tokens Work

  1. Insert: A unique token (e.g., CANARY_A3F8B2D1E9C4...) is placed in a sensitive file
  2. Monitor: Every tool result is scanned for canary token matches
  3. Detect: If a canary appears in output, it means the agent read the file and leaked its contents
  4. Alert: The violation is logged and the agent is notified

When To Use Canary Tokens

Use canaries when working with:

  • Credentials files (.env, config/credentials.yml, secrets.json)
  • Private key files (.pem, .key, SSH keys)
  • Database configurations (connection strings, migration files)
  • Internal documentation (architecture diagrams, security policies)
  • Any file the user flags as sensitive

Automatic Enforcement

When canary tokens are configured, the output validation handler automatically scans tool results for triggered canaries. Since tool_result handlers are side-effect only, the content will still reach you — but the violation is detected and flagged:

  1. The violation is logged with severity "critical"
  2. A status bar alert warns of possible data exfiltration
  3. The triggered canary is marked as triggered in the tracking store

What To Do When a Canary Is Triggered

  1. STOP — do not continue sending output that contains file contents
  2. Inform the user that a canary token was triggered (indicates data exfiltration risk)
  3. Do not reveal the canary token value itself
  4. Log the violation with guardrail_log_violation if not auto-logged
  5. Suggest remediation — the file may need to be excluded from agent access

MCP Bridge

When connected, guardrail_mcp provides canary management:

  • action: canary_insert — Insert a new canary into a file path
  • action: canary_check — Check text for triggered canaries
  • action: canary_list — List all active and triggered canaries

Read the full file on GitHub · 66 lines

Changes

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.

  1. 12d ago First seen · 66 lines · 22 tokens per session scan A 92dfbfd7404f

Subscribe to this mod's changes

Canary Tokens is a skill published in the GitHub repository TheArchitectit/agent-guardrails-template (79 stars, last pushed 3d ago), licensed BSD-3-Clause. It adds 22 tokens to every session and 772 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

construction-expert

Expert-level construction management, project planning, BIM, safety compliance, and construction technology. Use when the user mentions BIM, project management, safety, or building, or when the task involves Construction Management, Technologies, Standards and Regulations, or Cost Control.

personamanagmentlayer/pcl · 54 tokens

pydantic-ai

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

davila7/claude-code-templates · 32 tokens

edgeone skill scanner

A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.

Tencent/AI-Infra-Guard · 148 tokens

connect-agent

Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…

langwatch/langwatch · 102 tokens

dashboard-widgets

Author a dashboard widget — a small React component backed by named LangWatchQL queries — from a plain question. Discovers the analytics schema, writes the queries, writes the widget file, saves it, then proves it renders. Use when asked to build, prototype, or iterate on a custom chart widget, or to add a widget…

langwatch/langwatch · 79 tokens

agent-improve

Turns production evidence into tested improvements for your AI agent. Forms hypotheses from real traces and analytics, explains the reasoning behind each one, then executes with the user: scenario tests that reproduce production failures, prompt and code changes as reviewable PRs, new evaluators and monitors that…

langwatch/langwatch · 0 tokens