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/jongwony/epistemic-protocols/cursesnpx skills add jongwony/epistemic-protocols --skill cursesgit clone --depth 1 https://github.com/jongwony/epistemic-protocolsWrote 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/jongwony/epistemic-protocols/curses)<a href="https://agentmods.dev/skills/jongwony/epistemic-protocols/curses"><img src="https://agentmods.dev/badge/skills/jongwony/epistemic-protocols/curses.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 | $0.00024 | $0.02177 |
| Opus 5 | $0.00012 | $0.01089 |
| Sonnet 5 | $0.00005 | $0.00435 |
| Haiku 4.5 | $0.00002 | $0.00218 |
Grade A, and why
curses 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 5d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curses
Discover the structural costs hidden in your strengths.
Every strength casts a shadow. The shadow is not a flaw — it is the structural cost of a capability. Understanding the cost transforms a curse into a conscious trade-off.
When to Use
Invoke this skill when:
- Discovering structural costs hidden in your strengths
- Analyzing behavioral patterns for self-improvement recommendations
- Generating attitude principles and practice matrix
- Reflective questions about working patterns and their trade-offs
Skip when:
- Exploring philosophical tradition match (use /sophia instead)
- Quick single-protocol question (answer directly)
- No session history exists and user prefers manual exploration
Pipeline
| Phase | What | Mode |
|---|---|---|
| 1. Collect | Gather behavioral data | dimension-profiler agent |
| 2. Analyze | Strength-Shadow extraction | AI + user dialogue |
| 3. Recommend | Attitude principles + practice matrix | AI proposes |
| 4. Report | Generate HTML report | Automated |
If the user provides a specific question (e.g., "What are my curses?"), orient the analysis toward that question.
Phase 1: Data Collection
Same-session reuse: If dimension-profiler output is already available in this
conversation (from a prior /sophia or /curses run), skip Phase 1 entirely and
reuse that output. Both skills produce identical profiler results.
Two-step delegation (same pipeline as /sophia):
Step 1: Run coverage-scanner agent (see agents/coverage-scanner.md) to get
pre-aggregated session data (protocol counts, friction, session types, tools).
Step 2: Pass coverage output to dimension-profiler agent (see agents/dimension-profiler.md):
Analyze this user's behavioral dimensions from their session data.
coverage_data: [paste coverage-scanner output here]
data_sources:
rules_dir: {config_dir}/rules/
claude_md: {config_dir}/CLAUDE.md
settings_json: {config_dir}/settings.json
data_context: session-enriched
Return the dimension profile table with scores, confidence, and raw signals.
What ships with it
1 file 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.
- 5d ago First seen · 247 lines · 24 tokens per session scan A f00fffd8b197
curses is a skill published in the GitHub repository jongwony/epistemic-protocols (160 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 2,177 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 2026-08-30.
Other skills, from other repositories
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步(architecture-sync)。OpenCode / Claude / Codex / Cursor 通用。.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
taiyi-diagram-c4
TaiyiForge 辅助 — 从代码反推 C4 架构文档(Observed/Inferred 分层 · Mermaid 真源)。OpenCode / Claude / Codex / Cursor 通用。.
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.