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-motivational-interviewing-fidelity-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-motivational-interviewing-fidelity-auditor)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-motivational-interviewing-fidelity-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-motivational-interviewing-fidelity-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-motivational-interviewing-fidelity-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-motivational-interviewing-fidelity-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 | $0.00083 | $0.02049 |
| Opus 5.5 | $0.00033 | $0.00820 |
| Sonnet 5.5 | $0.00017 | $0.00410 |
| Haiku 4.5 | $0.00008 | $0.00205 |
Grade A, and why
call-motivational-interviewing-fidelity-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 9d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-motivational-interviewing-fidelity-auditor
Behavior-change calls deserve the same fidelity scrutiny clinicians get. Counts first, verdict second, honesty always.
This repo is full of health-call applications - refill reminders, adherence callbacks, care check-ins - and every one of them assumes the agent coached the patient rather than lectured them. Nothing in the sibling skills codes WHETHER the agent actually practiced Motivational Interviewing: did it reflect, ask open questions, gate advice behind permission - or did it slip into "you should" and "if you keep skipping" confrontation? This skill is a heuristic lexical coder inspired by the MITI 4.2.1 instrument: it classifies every agent sentence, counts the behaviors, derives the classic ratios, and grades a coarse verdict - abstaining honestly with NOT_MI_CALL when the callee never voiced any change talk. The counts and ratios are the product; the verdict is a coarse summary, not a clinical judgment.
When To Use
- after any behavior-change call - refill reminder, medication adherence, care check-in - before trusting that the agent coached rather than lectured
- when iterating on goal templates to improve agent style: run the audit, read the weakest counters, adjust the template, re-run
- as a gate between
get_call_runand any automation that acts on how the call went
When Not To Use
- as a clinical instrument or therapist QA; this is heuristic lexical coding of a phone agent, never a basis for evaluating human clinicians
- on calls with no change talk: NOT_MI_CALL is the honest abstention, not an error - grading agent style on a call that was never an MI conversation would be noise
- on non-English transcripts; all lexicons are English-only stems
- as a lie detector or intent test; it counts sentence shapes, it does not read minds
Verdicts
| Verdict | Meaning | Suggested routing |
|---|---|---|
MI_ADHERENT |
zero non-adherent behaviors, at least one reflection, open questions >= closed questions | proceed, keep the card as evidence |
PARTIALLY_ADHERENT |
catch-all: zero reflections, closed-heavy questioning, or scattered unpermitted advice below the threshold | review the weakest counters before trusting the style |
NON_ADHERENT |
any confrontation or warning, OR >= 3 pieces of advice without permission | a human reviews the call; template rework before more calls |
NOT_MI_CALL |
no callee change talk detected | abstain; do not grade style on a non-MI call |
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-call-result-nonadherent.json 1.0 KB
- references/example-call-result-not-mi.json 702 B
- references/example-call-result-partial.json 1.3 KB
- references/example-call-result.json 1.5 KB
- references/example-goal.txt 560 B
- references/examples.md 4.8 KB
- references/safety.md 3.3 KB
- scripts/motivational_interviewing_fidelity_auditor.py 15 KB runs code
- scripts/test_motivational_interviewing_fidelity_auditor.py 20 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.
- 9d ago First seen · 143 lines · 83 tokens per session scan A 78bc21f73f7e
call-motivational-interviewing-fidelity-auditor is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 2,049 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 2026-10-11.
Other skills, from other repositories
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
migrate-xunit-to-xunit-v3
Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
dart-test
DART Test: unit tests, integration tests, CI validation, and debugging.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
mobiai-ios-testing
Use when writing or running tests in an iOS project — unit tests, UI tests, snapshot tests, choosing the right framework.