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-temporal-anchor-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-temporal-anchor-auditor)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-temporal-anchor-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-temporal-anchor-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-temporal-anchor-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-temporal-anchor-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 | $0.00076 | $0.02545 |
| Opus 5.5 | $0.00030 | $0.01018 |
| Sonnet 5.5 | $0.00015 | $0.00509 |
| Haiku 4.5 | $0.00008 | $0.00254 |
Grade A, and why
call-temporal-anchor-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 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-temporal-anchor-auditor
A promise with no calendar anchor is a no-show waiting to happen.
CALL-E's highest-value calls are bookings: appointment-confirm,
no-show-shield, slotsaver, capacity-backfill-cascade all live or die
on whether the person on the other end walks in at the right slot. An agent
that closes with "see you tomorrow evening" or "your pickup is Tuesday at 2"
has exchanged a calendar anchor for a vibe - and each unanchored minute is
paid for later as a missed appointment, an idle bay, or a double-booked
table. This skill grades every time reference in the agent's own turns and
tells you which commitments would not survive a calendar check.
When To Use
- after any booking, confirmation, or appointment call, ideally with
--called-atset to the run's ISO-8601 start time so relative phrases ("tomorrow", "next month") resolve against a real reference date - whenever the transcript shows commitments but you cannot say, from the text alone, which calendar day and clock time the agent actually locked in
- before placing the next wave of calls, to craft a plan_call goal that forces absolute-time discipline (weekday + date + clock + meridiem)
When Not To Use
- without
--called-atwhen the relative phrases matter: without a reference time they gradeunresolvable_without_call_timeand weekday-date pair checks are skipped - if you know when the call ran, pass the flag - on non-English transcripts; the temporal lexicons are English-only
- to prove the callee misunderstood the time; the card grades the agent's wording only, never the callee's comprehension or intent
- during a call; strictly post-call analysis plus pre-call goal crafting
Verdicts
| Verdict | Meaning |
|---|---|
NO_TIME_REFERENCES |
the agent's turns contain no detectable time expression at all |
INTERNAL_DATE_CONFLICT |
the agent's own turns disagree with the calendar (stated weekday vs date) or restate a clock hour with a different value |
RELATIVE_ONLY_COMMITMENTS |
a commitment turn carries time expressions but never reaches a full absolute anchor anywhere the call supports it |
AMBIGUOUS_TIME_REFERENCES |
time references exist and no commitment failed, but ambiguous ones remain (dialect-dependent weekdays, day-part bands, meridiem-less clocks, week ranges) |
FULLY_ANCHORED |
every committed time resolves to an absolute date and a meridiem-bearing clock time |
What ships with it
8 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 456 B
- references/example-transcript-conflict.json 689 B
- references/example-transcript-relative.json 691 B
- references/example-transcript.json 787 B
- references/examples.md 7.1 KB
- references/safety.md 2.0 KB
- scripts/call_temporal_anchor_auditor.py 30 KB runs code
- scripts/test_call_temporal_anchor_auditor.py 27 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.
- 11d ago First seen · 183 lines · 76 tokens per session scan A 76dba39cc3e8
call-temporal-anchor-auditor is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 2,545 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 2026-10-09.
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…