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 abductive-reasoninggit 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/abductive-reasoning)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/abductive-reasoning"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/abductive-reasoning/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/abductive-reasoning"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/abductive-reasoning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Excessive Agency · line 3 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 74 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00116 | $0.01819 |
| Opus 5 | $0.00058 | $0.00910 |
| Sonnet 5 | $0.00023 | $0.00364 |
| Haiku 4.5 | $0.00012 | $0.00182 |
Grade A, and why
abductive-reasoning 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 10d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Abductive Reasoning
Overview
Abduction — inference to the best explanation — is the only mode of reasoning that introduces new ideas. Deduction works out consequences; induction generalizes instances; abduction generates the hypotheses themselves (Peirce, 1903).
Formal schema: The surprising fact C is observed. But if A were true, C would be a matter of course. Hence, there is reason to suspect A is true.
The "best" qualifier carries the weight: consistent-with-evidence is not enough — the hypothesis must beat rivals on coverage, simplicity, prior probability, and predictive power (Harman 1965; Lipton 2004).
Composes with bayesian-reasoning (Bayes scores hypotheses abduction generates), occams-razor (simplicity criterion), critical-thinking (competing-hypotheses analysis), and debugging-and-error-recovery (technical debugging is iterated abduction).
When to Use
- A surprising observation needs explanation (bug, symptom, outage, customer behavior, financial anomaly)
- A diagnostic decision must be made under uncertainty (medical, technical, investigative)
- Someone is treating "consistent with X" as proof of X
- A team has converged on one explanation without enumerating alternatives
- An investigation has stalled at the first plausible-sounding hypothesis
Not when: the problem is deductive (math, formal logic); evidence is sufficient for direct measurement; you have no domain knowledge to generate candidate hypotheses.
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: instead of "this looks like X, so it's X," abduction enumerates every hypothesis that would explain the observation and picks the one that best accounts for all the evidence — coverage, simplicity, prior plausibility, predictive power.
- Check fit: deductive / direct-observation problems → not this lens.
- Elicit the surprising observation — what happened that didn't match expectations?
[WAIT — do not advance until user responds]
- Run The Process one step at a time with their input — generate alternatives, score each on the four criteria.
[WAIT — do not advance until user responds]
- Close: name the chosen hypothesis, the closest rival, and the test that would distinguish them.
[WAIT — do not advance until user responds]
What ships with it
3 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.
- 10d ago First seen · 122 lines · 116 tokens per session scan A 86a81c2676de
abductive-reasoning is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 116 tokens to every session and 1,819 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…
journal-entry
Drafts correct double-entry journal entries from described business events, with templates for accruals, deferrals, depreciation, payroll, prepaids, and corrections. Every entry carries a date, memo, and support reference; reversals are drafted where due; a running debits-equal-credits check covers each entry and the…