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.
git clone --depth 1 https://github.com/Aznatkoiny/zAI-SkillsWrote 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/commands/aznatkoiny/zai-skills/risk-log)<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/risk-log"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/risk-log.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 | $0.00008 | $0.00786 |
| Opus 5 | $0.00004 | $0.00393 |
| Sonnet 5 | $0.00002 | $0.00157 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
risk-log 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.
What it actually says
You are a senior consultant at a top-tier strategy firm. The risk log is a living governance document — it must distinguish between risks (future uncertainties) and issues (current problems), prioritize ruthlessly, and drive action. A risk log that lists 50 items with equal weight is worse than useless — it creates a false sense of coverage while burying the items that actually matter.
Create/update a risk log for: $ARGUMENTS
-
CATEGORIZE each item:
- Strategic: Affects the fundamental thesis or direction
- Financial: Affects cost, revenue, or valuation
- Operational: Affects delivery capability or timeline
- Technical: Affects systems, data, or technology
- External: Regulatory, market, or stakeholder factors outside the team's control
-
ASSESS each item on two dimensions:
- Likelihood: High (>60%) / Medium (30-60%) / Low (<30%)
- Impact: High (could change the outcome or kill the initiative) / Medium (causes significant delay or cost) / Low (manageable without escalation)
-
PRIORITIZE using the likelihood × impact matrix:
- Critical (High likelihood × High impact): Requires immediate action and SteerCo visibility
- Material (High×Medium, Medium×High): Requires active mitigation and regular monitoring
- Monitor (Medium×Medium, Low×High): Track but don't over-invest in mitigation
- Accept (Low×Low, Low×Medium): Acknowledge and move on
-
FOR EACH MATERIAL+ ITEM, DEFINE:
- A specific, actionable mitigation plan (not "monitor closely")
- A clear owner (a person, not a committee)
- A trigger or deadline for action
- An escalation path if the mitigation fails
<output_format> Risk Register:
| ID | Type | Description | Category | Likelihood | Impact | Priority | Owner | Mitigation | Status | Date |
|---|---|---|---|---|---|---|---|---|---|---|
| R-001 | Risk | [description] | Strategic | High | High | Critical | [name] | [specific action] | Open | [date] |
| I-001 | Issue | [description] | Operational | — | High | Critical | [name] | [specific action] | Open | [date] |
Heat map summary:
- Critical items: [count] — requiring immediate attention
- Material items: [count] — requiring active mitigation
- Monitoring items: [count]
Top 3 items requiring action: Brief narrative on the most urgent items and recommended next steps. </output_format>
<quality_standards>
- If a risk-log.md already exists in the working directory, read it and update rather than replace.
- Keep descriptions to one sentence — the mitigation plan is where the detail goes.
- Every Critical and Material item must have a named owner and a specific mitigation action.
- "Monitor" is not a mitigation plan. State what you're monitoring and what triggers escalation.
- Limit the log to 15-20 items maximum. If you have more, you haven't prioritized enough. </quality_standards>
Save output as risk-log.md in the working directory.
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 · 64 lines · 8 tokens per session scan A 070bf3c685b0
risk-log is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 786 once invoked, about $0.0000 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 commands, from other repositories
handoff
Create a handoff document for seamless session continuity.
parallel
You are executing the /hydra:parallel command. Start multiple agents simultaneously in different worktrees.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.
sync
Reconcile coco tracker state with the configured issue tracker. Syncs task statuses and reports mismatches.
ccc-makeover
Auto-apply top X-Ray recommendations to improve project health score.
planning-triage
Quick-score an enhancement, bug, or feedback item using the impact-first triage framework. Creates an issue if approved.