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 sancovp/dinf --skill 0.1-dinfbanditgit clone --depth 1 https://github.com/sancovp/dinfWrote 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/sancovp/dinf/0.1-dinfbandit)<a href="https://agentmods.dev/skills/sancovp/dinf/0.1-dinfbandit"><img src="https://agentmods.dev/badge/skills/sancovp/dinf/0.1-dinfbandit/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/sancovp/dinf/0.1-dinfbandit"><img src="https://agentmods.dev/badge/skills/sancovp/dinf/0.1-dinfbandit.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 | $0.00011 | $0.00599 |
| Opus 5 | $0.00005 | $0.00300 |
| Sonnet 5 | $0.00002 | $0.00120 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade A, and why
0.1-dinfbandit 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 10d 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
This is a chain of reasoning (CoR) — a SPOKEN, paragraphical reasoning chain that ends in a DECISION. Say it as a paragraph; keep the moves in order.
CoR (custom syntax)
[Task] ⇒ [Recall] ⇒ [Decide] ⇒ [Execute] ⇒ |Reward|
Say it as a paragraph, in order
State your reasoning as ONE paragraph that, in order, 5 moves: Task, Recall, Decide, Execute, and finally converges on Reward. [Task: …the task is…] → [Recall: …have I done this…] → [Decide: …exploit…] → [Execute: …run the chain…] → [Reward: …the result is…]
Inner attention chain (use silently to generate the above)
Attention chain — DinfBandit
Attend, in order:
- Task
- Recall
- Decide
- Execute Hold: Reward ← converge attention here, then act
Index summary
[0.1] dinfbandit — a cor index node; opens to 4 branch(es): dinf-shape (ac), dinf-factor (ac), dinf-adjoin (ac), dinf-christen (ac). Reachable below: dinf-shape, dinf-factor, dinf-adjoin, dinf-christen.
Descend — the next layer (4)
Only this layer is loaded now. To descend, use the Read tool on a child below — that injects the child's layer (its persona + skills). A Bash cat reads the bytes but loads nothing; you must use the Read tool:
- 0.1.1-dinf-shape (ac): Read
dinfbandit/dinf-shape/.claude/skills/0.1.1-dinf-shape/SKILL.md - 0.1.2-dinf-factor (ac): Read
dinfbandit/dinf-factor/.claude/skills/0.1.2-dinf-factor/SKILL.md - 0.1.3-dinf-adjoin (ac): Read
dinfbandit/dinf-adjoin/.claude/skills/0.1.3-dinf-adjoin/SKILL.md - 0.1.4-dinf-christen (ac): Read
dinfbandit/dinf-christen/.claude/skills/0.1.4-dinf-christen/SKILL.md
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.
- 10d ago First seen · 36 lines · 11 tokens per session scan A ff70ba21c0a4
0.1-dinfbandit is a skill published in the GitHub repository sancovp/dinf (1 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 599 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
security-audit
Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and produce a structured findings report. Use when the user asks for a security review, an audit, or to check code for vulnerabilities. Report only — never fix.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
openkb-deck-editorial
A tool for creating a single-file HTML slide presentation from compiled knowledge-base content. Its visual style uses a warm cream background, serif typography, and brick-red accents.
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.