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 anchoringgit 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/anchoring)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/anchoring"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/anchoring.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 5.1 | $0.00127 | $0.02205 |
| Opus 5 | $0.00063 | $0.01103 |
| Sonnet 5 | $0.00025 | $0.00441 |
| Haiku 4.5 | $0.00013 | $0.00220 |
Grade A, and why
anchoring 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 6d 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.
Anchoring
Overview
When people estimate an unknown quantity they start from a reference point — an anchor — and adjust. The adjustment is almost always insufficient, so the final answer stays closer to the anchor than it should. This pattern holds even when the anchor is explicitly random and subjects are told to ignore it (Tversky & Kahneman 1974). It survives expertise, explicit warnings, and financial incentives for accuracy.
Strategically: almost every consequential negotiation, valuation, or forecast begins with an anchor. The first number said or written — asking price, salary band, prior-round valuation, revenue projection — anchors everything that follows.
Composes with: pricing-strategy · expected-value-and-kelly · probabilistic-thinking · signaling-games
When to Use
Apply when:
- About to negotiate a price, salary, valuation, contract term, or settlement
- Estimating an uncertain quantity after a number has already been mentioned
- A counterparty has opened and your reasoning is gravitating toward their number
- Resetting expectations after an anchor has already been set
- Sizing an AI startup valuation, raise, or AI-capex/adoption estimate where a headline round or a benchmark like Nvidia's market cap has already been floated as "the market"
When NOT to use:
- The number is genuinely informative (verifiable comparable, audited cost basis) — data, not an anchor
- Decision is trivial; you are past the negotiating phase; or anchor was set by you intentionally
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete 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 what-it-is: when you estimate or negotiate a number, the first number you hear pulls your answer toward it — even when you know it's random or wrong.
- Check fit against When to Use / When NOT to use. If the number is genuine data, say so.
- Elicit their real situation — a number that's been mentioned, an upcoming negotiation, a figure that's been floated. > [WAIT — do not advance until user responds]
- Walk through The Process one step at a time with their input. > [WAIT — do not advance until user responds]
- Close by naming the one concrete move that fits their situation (open with X / counter with Y / reset to Z). > [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.
- 6d ago First seen · 125 lines · 127 tokens per session scan A 4207e93081b9
anchoring is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 4d ago), licensed MIT. It adds 127 tokens to every session and 2,205 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.
maishou
A price-comparison workflow for products sold through major Chinese online marketplaces. It searches listings and can retrieve product details, purchase links, and available coupons.
crypto-report
Get cryptocurrency market data. Get Binance AI analysis report. Get blockchain news updates.
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…