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-repair-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-repair-sequence-auditor)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-repair-sequence-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-repair-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-repair-sequence-auditor"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-repair-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 | $0.00084 | $0.01248 |
| Opus 5.5 | $0.00034 | $0.00499 |
| Sonnet 5.5 | $0.00017 | $0.00250 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
call-repair-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 26d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-repair-sequence-auditor
"Sorry, what?" is data. An agent that plows past it manufactures a failed call.
Conversation analysis calls it other-initiated repair: the moments one speaker signals trouble in hearing or understanding. Human conversation runs about one repair every 1.4 minutes across languages. A phone agent that ignores a repair does not save time - it ends the call with a person who never understood the ask, which is exactly how a "confirmed" outcome turns out wrong later.
When To Use
- after any CALL-E call where the callee asked to repeat, slow down, or confirm which value was meant
- to decide whether a follow-up call should use a chunked, slower goal
- to generate that goal for
plan_calldirectly - to profile which agent wording keeps causing the trouble (digit-dense, long sentences, long words)
When Not To Use
- to detect sentiment or frustration; use
call-summarizerorcall-semantic-barge-in-analyzerfor pacing and cooperation - to repair an ambiguous email thread; that is
conversation-clarify, which decides whether to call - this skill audits what happened in a call already made - during a call; this is strictly post-call analysis plus pre-call goal crafting, because CALL-E exposes transcripts, not live audio
- as proof the person failed to understand; absent repairs can mean a clean call or an unengaged callee, and the card says so
Workflow
Audit a finished call
python3 scripts/repair_sequence_auditor.py analyze --transcript path/to/call-result.json
Reads the real get_call_run result shape ({status, result: {transcript}})
or the flat shape used by sibling skill fixtures. Emits a card:
repair_events[]: turn index, masked span,repair_type(open_class- "huh", "sorry?", "what?";repetition_request- "can you repeat that";candidate_understanding- "did you say X or Y";partial_repeat- quoting a fragment back with a question;specification_request- "which one", "can you slow down"),trouble_source_index+trouble_profile(digit_dense, long_words, long_sentence), andresolution(ADDRESSED/IGNORED/END_OF_CALL)repairs_initiated,unresolved_repairs,dominant_trouble_typecomprehension_trouble: LOW / MODERATE / HIGH (HIGH when 2+ repairs are ignored or 4+ repairs fire in one call)recommended_action:continue,verify_understanding_prompt, orredial_with_simplified_goal(with the goal text)
What ships with it
7 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-transcript-low.json 614 B
- references/example-transcript-moderate.json 717 B
- references/example-transcript.json 1.0 KB
- references/examples.md 7.9 KB
- references/safety.md 1.7 KB
- scripts/repair_sequence_auditor.py 17 KB runs code
- scripts/test_repair_sequence_auditor.py 18 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.
- 26d ago First seen · 102 lines · 84 tokens per session scan A 5b04a1e12ff7
call-repair-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 84 tokens to every session and 1,248 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 2026-09-24.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…