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 call-closing-sequence-auditorgit 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/call-closing-sequence-auditor)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-closing-sequence-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-closing-sequence-auditor/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/call-closing-sequence-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-closing-sequence-auditor.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 | $0.00082 | $0.01168 |
| Opus 5.5 | $0.00033 | $0.00467 |
| Sonnet 5.5 | $0.00016 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
call-closing-sequence-auditor 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 16d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-closing-sequence-auditor
The last twenty seconds are what the person repeats to their family. The body of the call is forgotten; the ending is the memory.
Closings are not hanging up. In conversation analysis they are an organized sequence the two parties co-produce: a pre-closing summary of what was settled, an arrangement for what happens next, a mutually exchanged goodbye. A call that stops short of that sequence leaves the person with unanswered questions, or with business introduced after the farewell that nobody can act on. This skill grades the shape of that final sequence on a finished CALL-E transcript.
When To Use
- after any outcome-bearing CALL-E call, before writing up the results
- in QA pipelines, to batch-scan finished transcripts for endings that need a follow-up touch
- before replaying calls with a tighter scripted closing, to compare ending shape across runs
When Not To Use
- as a satisfaction or call-quality score; the card measures sequence shape, not how the person felt
- when the callee hung up mid-flow; truncation by the caller is a legitimate ending and is not the agent's failure
- during a call; strictly post-call analysis plus pre-call goal crafting
- on non-English transcripts; every lexicon is English-only
Workflow
Audit a finished call
python3 scripts/closing_sequence_auditor.py analyze \
--transcript path/to/call-result.json
Reads the real get_call_run result shape ({status, result: {transcript}})
or the flat fixture shape used by sibling skill fixtures. The closing
window is the last 6 turns (the whole transcript if shorter); the six
checks are:
summary_present: an agent turn in the window that marks a summary ("just to confirm", "to recap", ...) or states a confirm verb ("booked", "confirmed", ...) backed by a concrete valuearrangement_present: an agent move that settles the next step ("we'll send", "you'll receive", "no further action", ...)terminal_exchange_complete: the agent said a farewell in the window and the callee said one anywhere after the first turndangling_question: the callee's last "?" received only farewells - or nothing at allpost_closing_business: the agent introduced values or questions after its own first farewellabrupt_end: no agent farewell in the window and the call stops on a question or a plain non-farewell turn
What ships with it
9 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.
- references/example-goal.txt 422 B
- references/example-transcript-abrupt.json 502 B
- references/example-transcript-dangling.json 528 B
- references/example-transcript-nosummary.json 552 B
- references/example-transcript.json 686 B
- references/examples.md 6.5 KB
- references/safety.md 1.7 KB
- scripts/closing_sequence_auditor.py 14 KB runs code
- scripts/test_closing_sequence_auditor.py 21 KB runs code
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.
- 16d ago First seen · 104 lines · 82 tokens per session scan A 652949a49632
call-closing-sequence-auditor is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,168 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 2026-10-04.
Other skills, from other repositories
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…