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 CALLE-AI/awesome-phone-call-agents --skill adherence-memory-callbackgit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote 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/calle-ai/awesome-phone-call-agents/adherence-memory-callback)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/adherence-memory-callback"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/adherence-memory-callback/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/calle-ai/awesome-phone-call-agents/adherence-memory-callback"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/adherence-memory-callback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00993 |
| Opus 5 | $0.00028 | $0.00496 |
| Sonnet 5 | $0.00011 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
adherence-memory-callback 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 8d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adherence Memory Callback
Use this skill when a pharmacy or clinic (with recipient consent) wants a brief outbound phone check-in on how a patient is getting on with a prescribed medicine — and wants the agent to get smarter with every call instead of starting from zero each time.
It packages a two-tier memory on top of a CALL-E outbound call:
- a sub-brain per caller (private running summary, open items, and any "call me back" context), and
- a shared master brain of general facts and anonymized signals learned across all callers, guarded so no single caller can poison it.
This skill only listens, acknowledges, and notes answers. It is not medical advice: it never diagnoses, never recommends a medicine or dose, and escalates anything serious to a human pharmacist.
When to use
- One outbound medication-adherence check-in to a consented patient number.
- You want per-caller continuity ("last time you mentioned…") and cross-caller learning (patterns several patients report).
- You want a human-in-the-loop gate before the agent starts proactively asking about a newly learned side effect.
When not to use
- Diagnosis, triage, dosing, emergency response, or any medical advice.
- Unsolicited outreach, marketing, or lead generation.
- Recurring schedules without a separate scheduler wrapper and explicit consent.
Workflow
- Read
references/safety.mdand confirm recipient consent and that it is not quiet hours for the caller's region. - Build the call goal from memory: the caller's sub-brain (continuity + any callback context) + the master brain's canonical facts (background) + any admin-approved proactive questions + the safety rails.
- Preview first (no call): run the reference app in
--dry-runmode to see the exact goal. - Place the call through CALL-E only after consent and guard checks pass.
- After the call, extract structured fields from the transcript and update memory: the sub-brain summary/open items, candidate facts (through the corroboration gate), and anonymized signals.
- If the caller asked to be called back, store the short reason so the next call opens with it ("last time you were at a wedding — how did it go?").
What ships with it
2 files 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.
- 8d ago First seen · 92 lines · 56 tokens per session scan A 1f1366a6df8a
adherence-memory-callback is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (88 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 993 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…