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 jongwony/epistemic-protocols --skill onboardgit 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/onboard)<a href="https://agentmods.dev/skills/jongwony/epistemic-protocols/onboard"><img src="https://agentmods.dev/badge/skills/jongwony/epistemic-protocols/onboard.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Data Exfiltration · line 419 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00022 | $0.06507 |
| Opus 5 | $0.00011 | $0.03254 |
| Sonnet 5 | $0.00004 | $0.01301 |
| Haiku 4.5 | $0.00002 | $0.00651 |
Grade A, and why
onboard 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 today.
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 — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard Skill
Start with a quick recommendation based on recent sessions, then optionally continue to guided learning — so users experience value first, learn second.
Invoke directly with /onboard when the user wants onboarding or protocol discovery.
When to Use
Invoke this skill when:
- A new user wants to discover which epistemic protocols fit their workflow
- A user wants to experience protocols through guided practice
- Re-onboarding after new protocols are added or workflow changes
Skip when:
- User already knows which protocol to use (direct invocation)
- Quick single-protocol question (answer directly)
Workflow Overview
Quick Proof: ENTRY → QUICKSCAN → PICK-1 → EVIDENCE → TRIAL → INSIGHT → NEXT
Targeted: ENTRY → QUICKSCAN → MAP → SCENARIO → TRIAL → QUIZ → GUIDE
Targeted + std: ENTRY → SCENARIO → TRIAL → QUIZ → GUIDE
| Phase | Owner | Tool | Purpose |
|---|---|---|---|
| 0. Entry | Main | Gate | Path selection: quick/targeted |
| 1. Quick Scan | Main | Glob, Read | User Context Profile extraction |
| 2a. Pick-1 | Main | — | Quick path: select 1 recommendation |
| 2b. Evidence | Main | — | Quick path: show 1 evidence card |
| 2. Map | Main | — | Targeted path: Profile → Protocol matching |
| 3. Scenario | Main | Gate | Targeted path: context-personalized intervention point |
| 4. Trial | Main | Gate | Real protocol execution (quick: mini trial, targeted: full trial) |
| 4→Q. Insight | Main | — | Quick path: post-trial insight card |
| 4→Q. Next | Main | Gate | Quick path: simplified navigation |
| 4→5 LOOP | Main | Gate | Targeted path: post-trial navigation |
| 5. Quiz | Main | Gate | Targeted path: Socratic protocol recognition quiz |
| 6. Guide | Main | Gate | Targeted path: summary + next protocol suggestion |
Data Sources
Compact mapping for inline use.
| Protocol | Cluster | When to Use | Key Patterns |
|---|---|---|---|
Aitesis /inquire |
Planning | AI is about to answer without enough observable context | External fact queries, verifiable grounding (for prior-session recall → use /recollect) |
Euporia /elicit |
Planning | Intent articulated but axis-undetermined; decision coordinates implicit in codebase / rules / past sessions | Multi-axis intent without single axis-specific protocol fit; substrate-implicit coordinates surface through cycle-emergent dimensions |
Heuresis /ideate |
Planning | Object-level candidate field is empty or has prematurely converged — widen it before any selection is made | Zero entry questions (seed vs. blank inferred from the utterance), frame-first mode on a blank entry, no elimination or ranking during generation, every candidate tagged origin ∈ {User, AI} |
Proplasma /preview |
Planning | Right before a direction commitment when the candidates cannot be judged from descriptions — contrast cheap discard-committed placeholder probes on user-settled axes | Principle-delegation at direction gates ("go with the recommended direction"), option-set reconstruction instead of choosing, "I'd have to see it" decision stalls |
Hypotyposis /sketch |
Planning | A form has to be made, intent cannot yet be settled from descriptions, and the user would recognize it on sight — sketch under a settled focus, take marks on a specific version, revise the retained version, finish on the recognized one | "I'd know it when I see it", a plan stalled at its first draft, a description rewritten repeatedly instead of made |
Prothesis /frame |
Analysis | Unsure which analytical perspective to use | Exploration ratio 3:1+ (Read+Grep+Glob vs Edit+Write) |
Analogia /ground |
Analysis | Checking if abstract advice fits your situation | Abstract pattern application without domain validation |
Periagoge /induce |
Analysis | Concrete cases accumulating into an unnamed essence — crystallize the emerging abstraction | 3+ instances with essence intuition but no located abstraction; /ground misfit where colimit is forced into substitution |
Merismos /apportion |
Execution | An autonomous goal is stated but its unit plan is uncompiled — cut it into coarse units at cited seams and close each unit before the run begins — a derived completion condition where one compiles, a recorded acceptance or a recorded reservation where none does | An unattended-run directive ("work through", "go through all", "run until done"), a goal that plainly exceeds one execution horizon, or a stop-hook being configured — each only shows an autonomous interval is intended, so the deciding check is whether the goal already carries units whose completion conditions are settled — closed by a determinate predicate, by a recorded acceptance, or by a recorded reservation; a plan that does is out of scope |
Epharmoge /contextualize |
Verification | Output is correct but doesn't fit the accumulated conversation context | Mismatch against session-built constraints (user-aware context accumulation) |
Elenchus /sublate |
Verification | About to externalize a working context whose apparent sufficiency has decayed | Dialectical antithesis per claim under test (provenance / counterfactual / cross-source consistency) before pre-execution sync |
Horismos /bound |
Cross-cutting | Deciding what to delegate to AI | Boundary probe, domain classification, BoundaryMap |
Anamnesis /recollect |
Cross-cutting | Resolving vague recall of prior sessions or discussions — one session, or a line of work, topic, or settled concept spread across several | Cross-session state recovery via narrative recognition (Recognition over Retrieval); a unit above one session is composed from its deposits at read time |
Katalepsis /grasp |
Cross-cutting | Rapid comprehension verification via intent-scented entry points | User-intent grasp for a target present in context and quotable, whoever produced it — reviews, plans, papers, docs, or code changes |
Hyphegesis /conduct |
Cross-cutting | Conducting the method of a multi-move work prospect before object-level cognition — order, independence, reconciliation, termination, routing | Multi-move work with non-trivial conduct (migrations, staged investigations, entangled adversarial/parallel/synthesis); "how should I approach this whole thing?" meta-questions |
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.
- today Changed · +1 lines 9aac7b11084b
- yesterday Changed · -1 lines edf83777899a
- 2d ago Changed · -7 lines c572bd99de09
- 4d ago Changed c12a08c08730
- 8d ago First seen · 439 lines · 22 tokens per session scan A 26ed612d39f2
onboard is a skill published in the GitHub repository jongwony/epistemic-protocols (160 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 6,507 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
rational-buddhism
A way to examine spiritual, supernatural, or other difficult-to-test claims using skepticism, personal testing, and scientific standards.
flow-next-audit
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
maestro-coach
Decision support and grounded teaching for the human. Invoke when the user signals a message did not land ("wait, what?", "I don't understand", "explain it like I'm five", "which is better?", "I'm not sure") about a question or fork they have been asked, or when they hand over a locked decision, a lesson, or a bundle…
workshop-facilitation
Design and facilitate consulting workshops, strategy offsites, discovery sessions, prioritization, and design sprints. Use for agendas, participant activities, facilitation guides, pre-work, and follow-through for in-person, virtual, or hybrid groups.
metacognitive-monitoring-ai-contexts
Design metacognitive checkpoints that prevent AI-assisted learning from bypassing genuine understanding. Use when students use AI tools and may overestimate their own comprehension.
self-explanation-prompt-designer
Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read material passively without engaging with underlying principles.