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 deciqAI/knowledge-skills --skill chestertons-fencegit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/chestertons-fence)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/chestertons-fence"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/chestertons-fence/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/deciqai/knowledge-skills/chestertons-fence"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/chestertons-fence.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 | $0.00124 | $0.01862 |
| Opus 5 | $0.00062 | $0.00931 |
| Sonnet 5 | $0.00025 | $0.00372 |
| Haiku 4.5 | $0.00012 | $0.00186 |
Grade A, and why
chestertons-fence 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 11d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chesterton's Fence
Overview
Before removing a rule, process, code path, or institution — you must understand why it was put there. Only when you can articulate the original purpose are you qualified to decide whether it still applies. Three components: (1) "I can't see the purpose" is evidence about you, not the fence; (2) investigation is mandatory, not optional; (3) demonstrated understanding is the prerequisite for change.
Composes with survivorship-bias, second-order-thinking, feedback-loops, first-principles.
When to Use
- A rule, process, code path, or practice is proposed for removal
- New leadership restructuring an organization with unfamiliar practices
- A developer "cleaning up" code whose purpose isn't documented
- A regulator or legislator repealing existing protections
- Someone says "why is this here?", "let's just remove this", "this seems useless"
- An AI-assisted rewrite/refactor proposes deleting an "ugly" guardrail, edge-case branch, validation, or manual review gate the model calls redundant
Not when: fence history is fully documented and purpose is confirmed obsolete; reformer is the original builder with full rationale understood.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete fence-removal case → run The Process directly.
- Coach mode: user is unfamiliar or has no concrete case → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- One-line: before removing a rule/code/process whose purpose you can't articulate, investigate — your inability to see the purpose is data about you, not the rule.
- Check fit: if the fence's history is fully documented and the purpose is clearly obsolete, the investigation is already done.
- Elicit the specific fence and proposed removal. What's being removed? Who proposes it? Why?
[WAIT — do not advance until user responds]
- One question at a time: when was the fence put there? by whom? what problem was it solving? does that problem still exist? are there other defenses?
[WAIT — do not advance until user responds]
- Close: investigation summary (purpose found / not found) + decision (remove / keep / modify) + documentation so the next reformer can read the history.
[WAIT — do not advance until user responds]
What ships with it
4 files 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.
- 11d ago First seen · 125 lines · 124 tokens per session scan A 8e95b962406d
chestertons-fence is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 9d ago), licensed MIT. It adds 124 tokens to every session and 1,862 once invoked, about $0.0006 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 skills, from other repositories
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
A weather-lookup workflow for Chinese locations, covering forecasts, hourly conditions, weather warnings, and daily-life indexes.
cto-advisor
Records technical decisions that serve a business outcome: constraints, architecture options, build-or-buy tradeoffs, and a justified skill selection. Use when the CEO asks "which architecture fits", "should we build or buy", "which skill should this department use", or "review our technical plan".
compliance-check
Compliance pre-flight for a feature, campaign, or initiative — maps the data and activity involved, checks applicable regimes (privacy/GDPR-style, consumer protection, marketing rules, sector-specific), lists required approvals and notices, builds a gap list with remediation owners, and ends in a go/no-go…
plan-payroll
Plans payroll cash: true loaded cost per hire (gross plus employer taxes, benefits, tools), a payroll calendar with cutoffs and cash-out dates, a scenario table for new hire vs raise vs contractor-vs-employee, and a payroll-to-revenue check against rough industry bands. Use when the user asks "can I afford to hire"…