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 lossless-group/lossless-agent-skills --skill lossless-crm-interface-guidelinesgit clone --depth 1 https://github.com/lossless-group/lossless-agent-skillsWrote 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/lossless-group/lossless-agent-skills/lossless-crm-interface-guidelines)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/lossless-crm-interface-guidelines"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/lossless-crm-interface-guidelines/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/lossless-group/lossless-agent-skills/lossless-crm-interface-guidelines"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/lossless-crm-interface-guidelines.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 | $0.00131 | $0.05802 |
| Opus 5 | $0.00066 | $0.02901 |
| Sonnet 5 | $0.00026 | $0.01160 |
| Haiku 4.5 | $0.00013 | $0.00580 |
Grade A, and why
lossless-crm-interface-guidelines 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 11d 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 — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lossless CRM Interface Guidelines
Operating manual for working inside the operator's Twenty CRM estate. Read before the first write of a session. The goal is a CRM that a partner could open cold and trust.
1. Who this is for
Load config/private.json before the first write of a session. This skill is
deliberately identity-free; every operator-specific value lives in that file, which is
gitignored. config/private.example.json is the public template — copy it to
config/private.json and fill it in.
If config/private.json is absent, say so and ask. Do not guess a name, a firm, or a
role, and do not backfill any of it from model knowledge.
Two blocks drive behaviour here:
-
operator— who the CRM belongs to. Used for attribution ("Per , ") and for the second-person voice this skill assumes. -
affiliations— the firm → role map, keyed by role (venturePartner,scout,informal). This is the only authority for the Deal ProspectMy Rolefield:affiliationskeyDeal Prospect My RoleventurePartnerVENTURE_PARTNERscoutSCOUTinformalINFORMAL
The operator is a career VC working across several firms rather than one house. Consequences:
- Never assume a company is "for the fund." Ask which firm, or leave routing unset.
- Never set
My Roleto a formal value for a firm that is not listed underventurePartnerorscoutinconfig/private.json. UseINFORMAL. - The same company can be routed to several firms with different rationales. That is the normal case, not an edge case.
- Read
affiliations.notesbefore acting on a firm — it records where a relationship is self-appointed or brokered through a person rather than a formal mandate.
They are a sophisticated operator. Do not hedge, do not lead with risk, do not warn about things a professional already knows. Lead with the upside case and what would have to be true for a fund-returner outcome. Risk matters only when it caps upside or kills the company. State it once, plainly, and move on.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 489 lines · 131 tokens per session scan A 28aa384d6af9
lossless-crm-interface-guidelines is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 18d ago), licensed MIT. It adds 131 tokens to every session and 5,802 once invoked, about $0.0007 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
session-review
End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one …
memory-audit
Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped…
second-opinion
Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique…
close-session
An end-of-session workflow that reviews new lessons, asks before promoting repeated patterns, refreshes memory files, and writes a handoff.
next-cache-components
Next.js 16 Cache Components guidance. Use when refactoring React Server Components for performance, debugging Partial Prerendering (PPR) issues, or applying the use cache directive, cacheLife, cacheTag, updateTag, and revalidateTag. Also use when deciding whether data should be static, cached, or dynamic, or when…
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK or build Model Context Protocol (MCP) servers. Load when creating stateful agents, durable workflows, MCP servers, checking MCP schema/error responses, or reviewing MCP code quality. Covers Agent class, state management, callable RPC, Workflows integration…