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 taxueseek/taxueskills --skill taxuegit clone --depth 1 https://github.com/taxueseek/taxueskillsWrote 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/taxueseek/taxueskills/taxue)<a href="https://agentmods.dev/skills/taxueseek/taxueskills/taxue"><img src="https://agentmods.dev/badge/skills/taxueseek/taxueskills/taxue/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/taxueseek/taxueskills/taxue"><img src="https://agentmods.dev/badge/skills/taxueseek/taxueskills/taxue.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 | $0.00288 | $0.05830 |
| Opus 5.5 | $0.00115 | $0.02332 |
| Sonnet 5.5 | $0.00058 | $0.01166 |
| Haiku 4.5 | $0.00029 | $0.00583 |
Grade A, and why
taxue 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 26d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
18 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.
- .archive/taxue-pre-outcome-first-20260715-132538.tar.gz 129 KB
- CHANGELOG.md 14 KB
- eval/cases.jsonl 3.2 KB
- references/combo_map.json 13 KB
- references/shared-rules.md 7.4 KB
- references/skill_registry.json 6.6 KB
- references/taxue-discipline.md 6.4 KB
- references/vault.md 2.3 KB
- scripts/__pycache__/_common.cpython-314.pyc 1.7 KB
- scripts/__pycache__/measure-outcome-first.cpython-314.pyc 8.9 KB
- scripts/__pycache__/taxue-quality-gate.cpython-314.pyc 27 KB
- scripts/_common.py 557 B runs code
- scripts/measure-outcome-first.py 5.9 KB runs code
- scripts/taxue-memory.py 7.5 KB runs code
- scripts/taxue-quality-gate.py 24 KB runs code
- SKILL.md.bak-pre-memory-post-20260715 15 KB
- SKILL.md.bak-v2.14 14 KB
- style-reference.md 17 KB
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.
- 26d ago Changed · +147 lines · +171 tokens per session 2f6394a5c53c
- 1mo ago First seen · 192 lines · 117 tokens per session scan A f7dfef357a70
taxue is a skill published in the GitHub repository taxueseek/taxueskills (24 stars, last pushed 27d ago), with no licence file. It adds 288 tokens to every session and 5,830 once invoked, about $0.0012 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
systems-thinking
Use when a problem involves interacting actors, feedback loops, delays, incentives, constraints, unintended consequences, or repeated patterns over time. Use when applying systems thinking, causal loop analysis, system mapping, leverage point identification, or dynamic complexity diagnosis.
break-even-analysis
Use when a commercial, operational, or investment decision needs a threshold for viability. Use when applying the Break Even Analysis consulting method and when a user asks for Break Even Analysis, method execution, structured diagnosis, or action planning.
communications-plan
Use when a decision, change, project, or stakeholder move needs coordinated communication. Use when applying the Communications Plan consulting method and when a user asks for Communications Plan, method execution, structured diagnosis, or action planning.
first-principles-thinking
Use when assumptions, analogies, legacy constraints, or accepted ways of working may be hiding a better solution. Use when applying First Principles Thinking, reasoning from fundamentals, assumption stripping, rebuilding from basic truths, or non-incremental problem solving.
kano-model
Use when deciding which customer needs or service features drive satisfaction, dissatisfaction, or differentiation. Use when applying the Kano Model consulting method and when a user asks for Kano Model, method execution, structured diagnosis, or action planning.
pricing-strategy-check
Use when designing, reviewing, or defending pricing for a product, service, project, or offer. Use when applying the Pricing Strategy Check consulting method and when a user asks for Pricing Strategy Check, method execution, structured diagnosis, or action planning.