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 toflow-ai/toflow-mcp --skill toflow-manage-crmgit clone --depth 1 https://github.com/toflow-ai/toflow-mcpWrote 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/toflow-ai/toflow-mcp/toflow-manage-crm)<a href="https://agentmods.dev/skills/toflow-ai/toflow-mcp/toflow-manage-crm"><img src="https://agentmods.dev/badge/skills/toflow-ai/toflow-mcp/toflow-manage-crm/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/toflow-ai/toflow-mcp/toflow-manage-crm"><img src="https://agentmods.dev/badge/skills/toflow-ai/toflow-mcp/toflow-manage-crm.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 | $0.00057 | $0.00830 |
| Opus 5.5 | $0.00023 | $0.00332 |
| Sonnet 5.5 | $0.00011 | $0.00166 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
toflow-manage-crm 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 4d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
toflow — Manage CRM Records
Covers the core CRM: people, companies, deals, custom attributes, and pipelines.
Before creating or updating anything
- Call
record_schema(orget_resource_schemafor custom fields) for the resource type (person,company,deal) to get the real attribute titles, types, and which are required — never guess a field name. Pass attribute titles as the keys in theattributesdict oncreate_record/update_record; forselect/multiselectfields, pass the value fromallowed_values, not the display label. - Call
filter_guidebefore anylist_recordscall that needs a non-trivial filter. Filters are a list ofFilterGroupobjects ({"logic": "and"|"or", "conditions": [{"field": "<Attribute Title>", "operator": "...", "value": ...}]}) — always wrap conditions in an explicit group rather than passing flat conditions. Operators:is,is_not,contains,not_contains,is_empty,is_not_empty,gt,lt,gte,lte,in.sortis a comma-separated"<Attribute Title>:asc|desc"string. If the user names a saved view, resolve it to aview_idvialist_viewsrather than guessing. - Call
list_recordswith filters/search first to check whether the record already exists — avoid creating duplicates. If you already have record IDs, pass them viaidsrather than loopingget_person/get_company/get_deal. Preferadd_people_to_list/add_companies_to_list(seetoflow-prospect-and-list) overcreate_recordwhen the source is a LinkedIn URL — those auto-create and dedupe.
Records
create_record/update_record(only provided fields change) /bulk_createfor batches.get_person/get_company/get_dealreturn the full profile including linked records and enrichment status (for people) — use these to get the complete picture before deciding next steps.delete_person/delete_company/delete_dealare soft-deletes — confirm with the user before calling any of them.list_company_categories/get_or_create_category— check for an existing category before creating one, to avoid duplicates.list_pipelines/list_stages— get valid IDs before setting a deal's stage viacreate_record/update_record.add_person_to_deal/remove_person_from_deal— link/unlink a contact to an opportunity.
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.
- 4d ago First seen · 37 lines · 57 tokens per session scan A c435ad775895
toflow-manage-crm is a skill published in the GitHub repository toflow-ai/toflow-mcp (6 stars, last pushed 5d ago), licensed MIT. It adds 57 tokens to every session and 830 once invoked, about $0.0002 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 2026-10-10.
Other skills, from other repositories
job-posting-intent
Detect buying intent from job postings. When a company posts a job in your problem area, they've allocated budget and are actively thinking about the problem. This skill finds those companies, qualifies them, extracts personalization context, and outputs everything to a Google Sheet. Does NOT do outreach — just…
contact-cache
Track all identified/contacted people across strategies. CSV-backed contact database with dedup by LinkedIn URL or email. Prevents duplicate outreach when running strategies on a recurring cadence.
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
deepline-org-chart
Build an interactive account org chart, leadership map, buying committee, or manager/report neighborhood around a person. Use for decision makers, reporting-line candidates, stakeholder mapping, and warm intro paths. Skip standalone email lookup and unrelated cross-company prospecting.
luma-event-campaign
DRAFT. Use when running a Luma-centered GTM event campaign: pull/export guests, enrich and score, draft invites and social, stage email+LI sequences paused for approval, and wire registration sync. Not installed by deepline skills.
event-ops-score-and-door
DRAFT. Score Luma/RSVP lists, approve against capacity, produce host-hit shortlists and day-of door packs. Systems framing — not a marketing CSV dump. Not installed by deepline skills.