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 raintr91/Processkit --skill business-impact-reviewgit clone --depth 1 https://github.com/raintr91/ProcesskitWrote 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/raintr91/processkit/business-impact-review)<a href="https://agentmods.dev/skills/raintr91/processkit/business-impact-review"><img src="https://agentmods.dev/badge/skills/raintr91/processkit/business-impact-review/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/raintr91/processkit/business-impact-review"><img src="https://agentmods.dev/badge/skills/raintr91/processkit/business-impact-review.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 | $0.00018 | $0.00722 |
| Opus 5.5 | $0.00007 | $0.00289 |
| Sonnet 5.5 | $0.00004 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
business-impact-review 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/business-impact-review
Read-only analysis by default. Do not implement fixes unless explicitly asked.
Checkout resolution
Cross-repo callers/callees:
| System id | Map |
|---|---|
legacy-* |
legacy-repos.local.json |
| Otherwise | platform-repos.local.json |
Missing/empty map or missing key → Gaps + /configure-repo-maps; never
guess paths. Then remind platform-dna codegraph:wire if needed. Ambiguous
matches → ask or Gaps.
Workflow
- Scope changed public/protected methods, routes, Jobs, Events, Listeners, Commands and Schedules from diff/user files.
- Search every direct and indirect caller; follow one hop beyond facade/dispatch/proxy boundaries.
- Trace each reachable vertical path:
Client/FE or Scheduler/Webhook
→ route/command/job
→ auth/middleware/context rewrite
→ controller/handler
→ service/domain
→ repository/model/database
→ event/listener/job/external API
→ response/error/status mapping
→ FE/consumer/next async hop
- Apply
risk-classes.md: authZ/IDOR, request bag, trust boundary, over-broad parse, null/empty, error collapsing, hardcode/magic, async context/idempotency, business rules, transactions and compatibility. - Report evidence and unsearched repos explicitly.
Required report
Summary / ship recommendation
Changed symbols
Horizontal callers
Vertical process paths
Findings: severity · class · evidence · impact · verify
Unsearched repos / residual risks
Targeted test plan
Accelerators (optional)
Route per intent (rule cross-repo-index.mdc): never one merged
workspace graph — always the correct per-repo index.
if CodeGraph available: changed symbols + callers + call graph — for repo X use
its own server `codegraph-<key>` (--project-root = X's checkout), never the
open repo's index; unindexed repo → report `cd <root> && codegraph init`
else: targeted repository search/read
if Docskit available: map process steps to CMP/CTR/FLOW docs via DOCSKIT_ROOT
(never CodeGraph for architecture Markdown)
else: repository conventions/search
IR / registry / generation questions → pointer kits
(CODEGENKIT_DOCS_ROOT, TESTKIT_DOCS_ROOT, TESTKIT_TESTS_ROOT)
if ArtifactGraph available: affected tags/registries/parity
(local-only — never a shared index for other repos)
else: model review from scoped evidence
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 · 91 lines · 18 tokens per session scan A 6622f51ed9eb
business-impact-review is a skill published in the GitHub repository raintr91/Processkit (1 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 722 once invoked, about $0.0001 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…