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-attest-challenge-authgit 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-attest-challenge-auth)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-attest-challenge-auth"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-attest-challenge-auth/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-attest-challenge-auth"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-attest-challenge-auth.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 | $0.00986 |
| Opus 5.5 | $0.00030 | $0.00394 |
| Sonnet 5.5 | $0.00015 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
call-attest-challenge-auth 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 29d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-attest-challenge-auth
An offline spoken-code coordination experiment.
This companion to dialtone-handshake generates an illustrative short code
derived from a pre-shared secret and checks a supplied transcript for a
fuzzy match. A matching code is only a text-level coordination signal;
recorded nonce reuse may indicate replay or an operator error. Neither
result authenticates a counterparty or authorizes sensitive disclosure.
When To Use
- to rehearse a coordination exchange between consenting test participants
- to flag a challenge recorded in the optional local nonce ledger
- to generate the challenge goal for
plan_calland the expected code to verify against
When Not To Use
- to recognize whether the other end is AI at all; use
dialtone-handshake - to authenticate humans; spoken codes leak through the audio channel to anyone listening
- against a determined man-in-the-middle who can hear and relay the code; this protocol does not defend against that (see safety.md)
- to authorize sensitive disclosure or any financial, medical, employment, safety or other consequential operation, even when the label is VERIFIED
Workflow
Craft the challenge
CALL_ATTEST_SECRET=<shared secret> python3 scripts/attest_auth.py craft --scenario attestation-call --language en
Reads the secret from the environment (never the command line), generates a nonce, derives the 4-token code (2 colors + 1 number word + 2 digits) from HMAC-SHA256(secret, nonce), and emits the plan_call goal that speaks the nonce. The expected code travels in the craft output only - keep it local.
Verify a finished call
python3 scripts/attest_auth.py verify --transcript path/to/call-result.json --nonce <nonce> --expected-code "BLUE ORANGE SEVEN 42" --ledger nonce-ledger.jsonl
Checks that an agent turn spoke the nonce and a callee turn replied; normalizes tokens (digit strings expand to digit words, FOR/TO/WON confusables fold) and fuzzy-matches with edit distance <= 1 per token in order. Emits a card:
What ships with it
6 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.
- 29d ago First seen · 98 lines · 74 tokens per session scan A 374b1cd2a7a3
call-attest-challenge-auth is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 986 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 2026-09-21.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.