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 hiendinhngoc/unknowns --skill unknownsgit clone --depth 1 https://github.com/hiendinhngoc/unknownsWrote 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/hiendinhngoc/unknowns/unknowns)<a href="https://agentmods.dev/skills/hiendinhngoc/unknowns/unknowns"><img src="https://agentmods.dev/badge/skills/hiendinhngoc/unknowns/unknowns.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 | $0.00064 | $0.00625 |
| Opus 5 | $0.00032 | $0.00313 |
| Sonnet 5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
unknowns 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 7d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unknowns Orchestrator
Pure router. Detect the phase, invoke the right skill via the Skill tool. If this agent has no skill-invocation tool, read that skill's SKILL.md and follow it directly. No technique logic lives here.
Phase detection
Trust explicit conversation intent first: requests to review/merge, reports of a plan deviation, porting language, or prototype language route directly. Use git only when intent is not clear.
When git evidence is needed, resolve the comparison base in this order: the
current branch's configured upstream; refs/remotes/origin/HEAD; an existing
local main; then master. Verify every candidate before using it.
Then check, in order:
Incidental dirt is not evidence: modifications limited to generated or
IDE-managed files (*.pbxproj, lockfiles, .DS_Store, build outputs) do not
indicate a task in flight — treat such a worktree as clean.
- Pre-merge: the user expresses review/merge intent, or HEAD has commits
ahead of the resolved base and the worktree has no tracked modifications →
invoke
unknowns:merge-quiz. - Mid-implementation: tracked modifications exist that plausibly belong to
the task at hand, or the conversation shows
an agreed plan being executed → if a deviation was just discussed, invoke
unknowns:log-deviation; otherwise report that no concrete deviation is available to log and present the three pre-implementation techniques without invoking one speculatively. - Pre-implementation: no changes yet for the task at hand → ask ONE
question: what kind of unknown are they facing?
- Unfamiliar system / risky area → invoke
unknowns:blindspot - Porting or adapting existing code → invoke
unknowns:verify-ref - Undecided UX or behavior → invoke
unknowns:mock
- Unfamiliar system / risky area → invoke
Rules
- Route and invoke — never inline a technique's logic here.
- If git state and conversation disagree, trust explicit conversation intent.
- Outside a git repo, route from conversation; ask one phase question only when no intent or target can be inferred.
- Skill names here use the
unknowns:namespace (Claude Code plugin install). If the skills were installed flat (Codex, OpenCode:cp -r skills/*), they go by their bare directory names —blindspot,verify-ref,mock,log-deviation,merge-quiz.
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.
- 7d ago First seen · 56 lines · 64 tokens per session scan A ada6b93fc3ba
unknowns is a skill published in the GitHub repository hiendinhngoc/unknowns (9 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 625 once invoked, about $0.0003 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
fast-resume
Search local coding-agent session history and identify safe resume commands. Use when the user asks to find, inspect, continue, or recover previous work from Claude Code, Codex, Pi, or another agent indexed by fast-resume.
kanban-orchestrator
Kanban orchestrator: decompose, route, verify. No executing.
kunpeng-skill
A local research assistant that collects and distills information from projects, websites, apps, media, articles, books, and courses. It turns the material into a searchable library of methods and patterns.
exploit-xss
Cross-site scripting (XSS) vulnerability detection and exploitation. Supports reflected XSS, stored XSS, DOM-based XSS, and blind XSS testing. Use this skill when user mentions XSS, cross-site scripting, script injection, or needs to test JavaScript injection in parameters, forms, headers, or DOM sources.
results-storage
SQLite-based persistent storage and reporting system for penetration testing results. Use this skill when user needs to store scan results, query vulnerabilities, generate reports, or manage pentest data across sessions.
exploit-sqli
SQL injection detection and exploitation using sqlmap, manual techniques, and custom payloads. Use this skill when user needs to test for SQL injection vulnerabilities, extract database information, or exploit SQLi in parameters, headers, or cookies.