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 bekservice/Famulor-Skill --skill famulor-assistants-historygit clone --depth 1 https://github.com/bekservice/Famulor-SkillWrote 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/bekservice/famulor-skill/famulor-assistants-history)<a href="https://agentmods.dev/skills/bekservice/famulor-skill/famulor-assistants-history"><img src="https://agentmods.dev/badge/skills/bekservice/famulor-skill/famulor-assistants-history/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/bekservice/famulor-skill/famulor-assistants-history"><img src="https://agentmods.dev/badge/skills/bekservice/famulor-skill/famulor-assistants-history.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 | $0.00074 | $0.00646 |
| Opus 5.5 | $0.00030 | $0.00258 |
| Sonnet 5.5 | $0.00015 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
famulor-assistants-history 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 today.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Famulor Assistants & Omnichannel History
Use the OAuth-secured Famulor MCP profile at:
https://app.famulor.io/mcp?profile=assistant-history
This marketplace profile is intentionally read-only. It exposes exactly 11 tools:
| Tool | Use |
|---|---|
list_assistants |
List assistants visible in the authenticated workspace. |
get_assistant |
Read one assistant's configuration. |
list_assistant_versions |
List saved versions for an assistant. |
get_assistant_version |
Read one saved assistant version. |
list_prompt_templates |
List available prompt templates. |
get_languages |
List supported language options. |
get_models |
List models available to the workspace. |
get_voices |
List available voices. |
list_history |
Search unified call, messaging, and email history. |
get_call |
Read full details for one call returned by history. |
get_email_history_item |
Read the full email thread for one email history item. |
Workflow
- Confirm which authenticated Famulor workspace the user means when it is ambiguous.
- Use a
list_*tool to find the exact resource or history item instead of guessing an ID. - Use the matching
get_*tool when the user needs full detail. - Summarize only the fields returned by the server and preserve the distinction between configured values and observed history.
list_history is the omnichannel overview. It may include voice calls, emails, and messaging conversations from connected channels such as Instagram or Messenger. Messaging entries can be previews rather than complete chat transcripts; never claim a full conversation unless the server actually returned it. Use get_call for call detail and get_email_history_item for an email thread.
Safety and access boundaries
- Keep every request read-only. This profile cannot create, update, delete, send, call, launch, purchase, transfer, or configure anything.
- Do not bypass the restricted profile when a user requests a write action. Explain that the installed marketplace integration supports Assistant & History review only.
- Never infer access across workspaces. OAuth scopes, workspace membership, role, plan, retention, and server-side policy remain authoritative.
- Treat transcripts, recordings, messages, emails, contacts, and customer context as personal data. Return only what is necessary for the request.
- Use live tool schemas for arguments and availability; do not invent IDs, enum values, or fields.
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.
- today Changed ff2c284d6ac5
- 6d ago Changed 08dd205635de
- 7d ago Changed 13470c3b94e1
- 20d ago Changed 2bf78ecbaac4
- 29d ago Changed 2789f1e6c0a8
- 1mo ago First seen · 51 lines · 74 tokens per session scan A d47ddbacfdb0
famulor-assistants-history is a skill published in the GitHub repository bekservice/Famulor-Skill (2 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 646 once invoked, about $0.0003 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
helm-bjw-s-chart
Generate production-ready Helm charts on the bjw-s-labs common library (app-template v5, v4 legacy). Use for new charts, Compose-to-Helm conversion, sidecars, init containers, services, ingress, persistence, StatefulSets, HPAs, Service/PodMonitors, and NetworkPolicies.
dockerfile-best-practices
Create and optimize Dockerfiles and Compose files with BuildKit, multi-stage builds, cache mounts, and non-root hardening. Also triggers on container images, build performance, or Docker security, even without the word 'Dockerfile'.
apple-shortcuts
Generate importable Apple Shortcuts (.shortcut / plist XML) for macOS and iOS. Use this skill whenever the user wants to create, modify, reverse-engineer, or understand Apple Shortcuts, including native actions, third-party app integrations (Actions, Data Jar, Toolbox Pro, Scriptable, a-Shell, Jayson, Pushcut)…
github-actions
Use this skill when authoring or debugging GitHub Actions workflows (.github/workflows/.yml) — e.g. "add CI for this Drupal project on GitHub", "run phpcs/phpstan/phpunit on pull requests", "cache composer dependencies", "deploy over SSH when main is pushed", "why didn't my workflow trigger", or anything involving…
gitlab-ci
Use this skill when authoring or debugging GitLab CI/CD pipelines (.gitlab-ci.yml) — e.g. "add a CI pipeline for this Drupal project", "run phpcs/phpstan/phpunit in GitLab CI", "deploy with drush from a pipeline", "why is my job not running", "cache composer dependencies", or anything involving stages, rules…
docker-compose
Use this skill when authoring or editing Docker Compose files (compose.yaml / docker-compose.yml), running multi-container stacks, or containerizing a Drupal/PHP application — e.g. "set up a local Drupal stack with nginx and MariaDB", "add Redis to my compose file", "why won't my containers start", "split dev and prod…