Borrowing it
Nothing to install: this file belongs to stoa-platform/stoa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stoa-platform/stoa/main/.claude/skills/impact/SKILL.mdgit clone --depth 1 https://github.com/stoa-platform/stoaWrote 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/stoa-platform/stoa/impact)<a href="https://agentmods.dev/skills/stoa-platform/stoa/impact"><img src="https://agentmods.dev/badge/skills/stoa-platform/stoa/impact/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/stoa-platform/stoa/impact"><img src="https://agentmods.dev/badge/skills/stoa-platform/stoa/impact.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 | $0.00000 | $0.00488 |
| Opus 5.5 | $0.00000 | $0.00195 |
| Sonnet 5.5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
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 2mo 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
/impact — Service Impact Analysis
Trigger
User runs /impact <service> to answer: "If I kill this service, what breaks?"
Steps
1. Validate Service
./scripts/ops/catalog-graph.sh --reverse <service>
If service not found, show the error (lists available services).
2. Show Reverse Dependencies
Display the table output from --reverse — shows all impacted services with depth (direct vs transitive) and type.
3. Show Impact Graph
./scripts/ops/catalog-graph.sh --impact <service>
Display the Mermaid subgraph (colored: red=down, orange=direct, yellow=transitive).
4. Enrich with Live State (optional)
If kubectl is available and configured, enrich with pod status:
# For each impacted service, check live state
kubectl get pods -n stoa-system -l app=<service-name> -o wide --no-headers 2>/dev/null
Present enriched table:
| Service | Impact | Pods | Status | Image |
|---|---|---|---|---|
| control-plane-api | direct | 2/2 | Running | ghcr.io/stoa-platform/control-plane-api:latest |
| control-plane-ui | transitive | 1/1 | Running | ghcr.io/stoa-platform/control-plane-ui:latest |
If kubectl is unavailable, skip enrichment and note: "kubectl not available — showing static graph only."
5. Summary
Output a one-line blast radius summary:
Blast radius: N services impacted (X direct, Y transitive) across Z types
Modes
| Command | Output |
|---|---|
/impact <service> |
Full analysis (table + graph + live enrichment) |
/impact <service> --static |
Skip kubectl enrichment (graph only) |
Rules
- Read-only — never modify any service or infrastructure
- No IPs — never display IP addresses in output
- No secrets — never display secret values
- Graceful degradation — if kubectl fails, fall back to static graph
- Catalog is source of truth — live state enriches but doesn't replace catalog data
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.
- 2mo ago First seen · 69 lines · 0 tokens per session scan A 7c1352bbd012
impact is a skill published in the GitHub repository stoa-platform/stoa (9 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 488 tokens. 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.
impact compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| impactstoa-platform/stoa | Skill | 9 | yesterday | Apache-2.0 | A | 0 | Claude Code |
| lyrikgebruder/wirken | Skill | 194 | 2d ago | MIT | A | 15 | Claude Code |
| librariangebruder/wirken | Skill | 194 | 2d ago | MIT | A | 34 | Claude Code |
| notesgebruder/wirken | Skill | 194 | 2d ago | MIT | A | 10 | Claude Code |
| tdx-assetsgebruder/wirken | Skill | 194 | 2d ago | MIT | A | 58 | Claude Code |
| aggregatorgebruder/wirken | Skill | 194 | 2d ago | MIT | A | 30 | Claude Code |
| githubgebruder/wirken | Skill | 194 | 2d ago | MIT | A | 9 | Claude Code |