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 panbanda/omen --skill assess-impactgit clone --depth 1 https://github.com/panbanda/omenWrote 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/panbanda/omen/assess-impact)<a href="https://agentmods.dev/skills/panbanda/omen/assess-impact"><img src="https://agentmods.dev/badge/skills/panbanda/omen/assess-impact.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00749 |
| Opus 5 | $0.00017 | $0.00375 |
| Sonnet 5 | $0.00007 | $0.00150 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
assess-impact 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 8d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess Impact
Understand the potential blast radius of changes before making them by analyzing dependencies, coupling patterns, and ownership.
Prerequisites
Omen CLI must be installed and available in PATH.
Workflow
Step 1: Check Symbol Blast Radius
Use the impact command to get transitive callers and callees in one call:
omen -f json impact <symbol-name> --depth 2
This returns affected files, caller/callee BFS levels, and the total count — much faster than building the picture manually.
To inspect a specific symbol first:
omen -f json symbol <symbol-name>
Step 2: Map File-Level Dependencies
Run the dependency graph analysis for file-level coupling:
omen -f json graph --compact
Identify:
- Direct dependents (files that import the target)
- Transitive dependents (files that import the dependents)
Step 3: Check Temporal Coupling
Run the temporal coupling analysis:
omen -f json temporal
Files with high temporal coupling to the target often need to change together even without explicit imports.
Step 3: Identify Stakeholders
Run the ownership analysis:
omen -f json ownership
Identify:
- Primary owner of the target file
- Owners of dependent files
- Subject matter experts to consult
Impact Categories
Classify impact by type:
| Category | Description | Action |
|---|---|---|
| Direct | Explicit imports/calls | Will break if signature changes |
| Implicit | Temporal coupling | May break due to shared assumptions |
| Behavioral | Same owner/team | Likely understands the change |
| Unknown | No coupling, different owner | Needs extra review |
Output Format
Present impact analysis as:
# Change Impact: `target/file.go:FunctionName`
## Direct Dependencies (will break)
- `consumer/a.go` - calls FunctionName directly
- `consumer/b.go` - uses returned type
- `test/target_test.go` - tests the function
## Implicit Dependencies (may break)
- `related/cache.go` - 0.85 temporal coupling
- Always changes with target
- Likely shares state or assumptions
- `related/config.go` - 0.72 temporal coupling
- Often changes together
- May depend on same configuration
## Stakeholders to Notify
- [email protected] - Primary owner of target (85% of commits)
- [email protected] - Owns consumer/a.go
- [email protected] - Owns related/cache.go
## Risk Assessment
- **Blast Radius**: 5 files directly, 12 files transitively
- **Coupling Risk**: 2 files with implicit dependencies
- **Team Impact**: 3 developers should be notified
## Recommended Approach
1. Coordinate with alice (primary owner)
2. Update tests in target_test.go first
3. Check related/cache.go for shared assumptions
4. Notify bob and charlie before merging
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.
- 8d ago First seen · 123 lines · 35 tokens per session scan A 2080e8e9bf2a
assess-impact is a skill published in the GitHub repository panbanda/omen (19 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 749 once invoked, about $0.0002 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
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.