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 agentmods add skills/global-slice/claude-plugin/workflows-analysisnpx skills add Global-Slice/claude-plugin --skill workflows-analysisgit clone --depth 1 https://github.com/Global-Slice/claude-pluginWhat 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 | $0.00067 | $0.01204 |
| Opus 5 | $0.00034 | $0.00602 |
| Sonnet 5 | $0.00013 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
workflows-analysis 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflows Analysis
Scope
Use for workflow process state, payments, and tax withholding. MCP cannot approve or mutate workflows. For compliance tickets, use compliance-analysis. For grant economics or vesting, use securities-analysis or equity-compensation-analysis.
Core Principle
Workflow tools are read-only operational views. Use them to inspect process state, documents, payments, tax withholding, trustee updates, and workflow progress. Do not imply that MCP can approve, run, resend, cancel, or mutate workflows.
Start broad with workflow pages, then fetch one workflow only after you have a UUID. Use securities, stakeholder, cap-table, compliance, and valuation tools for business context; workflow tools show process state, not the full source-of-truth economics.
Supported Workflow Types
workflows_list and workflows_get_one require type to be one of:
grantLetter: grant or award letter execution workflows.corporateApproval: board/corporate approval workflows for grants.shareCertificate: share certificate signing and delivery workflows.exercise: exercise request workflows, including exercise notice, payment, tax withholding, share issuance, and optional share certificate steps.
Use the exact enum values above. Do not pass internal workflow enum names such as executeAwardLetter or exerciseRequestNested to the MCP workflow tools.
Tool Selection
- Use
workflows_listfor discovery by workflow type. It returns{ type, data }with the page payload for that type. - Use
workflows_get_onewhen you have amainWorkflowExecutionIdor workflow UUID and need details for one workflow. - Use
payments_get_pending_listfor pending exercise-payment reconciliation rows across the company. - Use
tax_withholding_get_listfor exercise tax-withholding rows across the company. - Use securities or stakeholder tools to resolve IDs found in workflow rows when the user asks about the underlying grant, share, stakeholder, or ownership impact.
- Use compliance tools separately if the user asks whether a workflow has compliance tickets or blockers.
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.
- 2d ago First seen · 74 lines · 67 tokens per session scan A a2f948a023fc
workflows-analysis is a skill published in the GitHub repository Global-Slice/claude-plugin (9 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,204 once invoked, about $0.0003 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 skills, from other repositories
cap-table-management
Manage the capitalization table — track all equity holders, SAFEs and convertible notes, model dilution scenarios, and maintain a fully diluted view. Use when the user asks about updating the cap table, modeling dilution, converting SAFEs, managing the option pool, or understanding ownership percentages.
equity-deep-dive
A thorough single-equity deep dive — read the recent qualitative picture from the web, then ground it in fundamentals and health ratios, an intrinsic DCF with a sensitivity range, a comparable-company cross-check, and the analyst-consensus view.
dcf-valuation
Estimate a public equity's intrinsic value with a discounted-cash-flow model — pull fundamentals, set a discount rate via CAPM/WACC, project free cash flow, and discount it.
relative-valuation
Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios.
consensus-check
Summarize the sell-side view on an equity — analyst price targets, forward EPS/revenue estimates and ratings — and corroborate it against recent guidance and estimate revisions from the web.
ticker-snapshot
Quick structured overview of a single public equity — identity, sector, market cap, valuation ratios, current price, recent trend.