impact

A skill for finding enough backlog work to bring a sprint to about 80% of the team’s established delivery rate. A sprint is a fixed work period, and velocity is the amount a team has reliably completed before.

In plain words
What is it for?
Reading the current Linear cycle, checking available backlog items, filtering by roadmap theme when requested, and either reporting or promoting suitable work depending on the selected mode.
Why use it?
It shows whether the current sprint has a capacity gap and ranks possible work from several backlog sources instead of filling the plan by guesswork.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/stoa-platform/stoa/impact
Any agent
npx skills add stoa-platform/stoa --skill impact
Clone the repo
git clone --depth 1 https://github.com/stoa-platform/stoa

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00488
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 2d ago against content hash 7c1352bbd012, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.claude/skills/impact/SKILL.md · 69 lines

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
Changes

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.

  1. 2d ago First seen · 69 lines · 0 tokens per session scan A 7c1352bbd012

Subscribe to this mod's changes

impact is a skill published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), 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.