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 agentmods add skills/getaxonflow/axonflow-claude-plugin/explain-decisionnpx skills add getaxonflow/axonflow-claude-plugin --skill explain-decisiongit clone --depth 1 https://github.com/getaxonflow/axonflow-claude-pluginWrote 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/getaxonflow/axonflow-claude-plugin/explain-decision)<a href="https://agentmods.dev/skills/getaxonflow/axonflow-claude-plugin/explain-decision"><img src="https://agentmods.dev/badge/skills/getaxonflow/axonflow-claude-plugin/explain-decision.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 | $0.00029 | $0.00267 |
| Opus 5 | $0.00015 | $0.00133 |
| Sonnet 5 | $0.00006 | $0.00053 |
| Haiku 4.5 | $0.00003 | $0.00027 |
Grade A, and why
explain-decision 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.
What it actually says
Use this skill when a user asks "why was that blocked?", "what policy fired?", or wants the context behind an allow/deny before retrying or requesting an override.
Call the explain_decision MCP tool with the decision_id returned in the original policy-check response (e.g. decision_id on a check_policy response or in the deny block reason).
The response includes:
policy_matches[]— every matched policy withpolicy_id,policy_name,risk_level, andallow_overridedecision—"allow"or"deny"reason— human-readable summaryrisk_level—critical,high,medium,lowoverride_available— whether the caller can request a session overridehistorical_hit_count_session— how often this exact decision_id pattern has fired in the rolling 24h window
Present the result as a short summary: which policy fired, the risk level, whether an override is available, and (if so) suggest the user invoke create-override with a justification.
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 · 20 lines · 29 tokens per session scan A 1f5080407a6b
explain-decision is a skill published in the GitHub repository getaxonflow/axonflow-claude-plugin (4 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 267 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 2026-08-31.
Other skills, from other repositories
unslop
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle…
unslop-file
Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly. Two modes: --deterministic (fast, regex-based, no API) and LLM (default, calls Claude for rewrite). Humanized version…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
unslop-help
Quick-reference card for unslop modes, sub-skills, and slash commands. One-shot display, not a persistent mode. Trigger: /unslop-help, "unslop help", "what unslop commands", "how do I use unslop".
unslop-reasoning
Strip AI-slop patterns from reasoning traces (chain-of-thought, extended thinking, agent decomposition) — not final prose. Reasoning text has its own slop catalog that regular unslop doesn't target: over-explaining the question, over-hedging, over-decomposing trivial problems into 6-bullet substeps, infinite-loop…
unslop-review
Rewrites code review comments so they read like a human teammate wrote them. Cuts corporate-AI throat-clearing ("I noticed...", "I was wondering if perhaps...", "It might be worth considering..."). Each comment is direct: location, the issue, a concrete fix. Use when user says "humanize review", "de-slop PR comment"…