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 shawnla90/recursive-drift --skill _templategit clone --depth 1 https://github.com/shawnla90/recursive-driftWrote 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/shawnla90/recursive-drift/_template)<a href="https://agentmods.dev/skills/shawnla90/recursive-drift/_template"><img src="https://agentmods.dev/badge/skills/shawnla90/recursive-drift/_template/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/shawnla90/recursive-drift/_template"><img src="https://agentmods.dev/badge/skills/shawnla90/recursive-drift/_template.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 | $0.00016 | $0.00148 |
| Opus 5.5 | $0.00006 | $0.00059 |
| Sonnet 5.5 | $0.00003 | $0.00030 |
| Haiku 4.5 | $0.00002 | $0.00015 |
Grade A, and why
skill-name 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.
What it actually says
Skill Name
Brief description of the skill's purpose.
When to Invoke
- [Trigger condition 1]
- [Trigger condition 2]
- [Manual trigger: user types
/skill-name]
Steps
Step 1: [Action]
[Instructions]
Step 2: [Action]
[Instructions]
Step 3: [Action]
[Instructions]
Output
- Location: [Where the output goes]
- Format: [What it looks like]
Rules
- [Constraint 1]
- [Constraint 2]
- [Constraint 3]
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 · 37 lines · 16 tokens per session scan A 5639fc8a75b7
skill-name is a skill published in the GitHub repository shawnla90/recursive-drift (17 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 148 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.
agent-engineering
Decision framework for which agent-engineering mechanism, if any, fits a workflow problem: durable rule, skill, hard constraint, verification, eval, eval harness, feature map, observability, or increased automation/trust. Use whenever agents keep breaking something, a change isn't trusted yet, it's unclear if Claude…
init
Set up project docs, coding standards, architecture, and ADR scaffolding. Works for greenfield and existing repos.
cotend-diagnose-only
A read-only investigation mode for finding root causes, semantic drift, or incomplete capabilities before making changes. It prevents project files from being edited during diagnosis.
cotend-model-upgrade
Use when a project may benefit from a stronger model or changes carrier, provider, actual model, material configuration, or role. Separate identity and role; classify advisor, trial, confirmed-primary, and rollback changes; prepare evidence-backed advisor or takeover packets; make non-authorizing Full/Adaptive…
cotend-tooling
Inventory, reconcile, collect, verify, index, find, evaluate, adopt, refresh, or retire reusable development capabilities such as Skills, MCPs, libraries, services, CLIs, GitHub projects, and technical articles. Use for an explicit project tooling inventory/reconcile, tooling/library search, a supplied tool or post…