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 sumitaich1998/OpenDate --skill conversation-recoverygit clone --depth 1 https://github.com/sumitaich1998/OpenDateWrote 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/sumitaich1998/opendate/conversation-recovery)<a href="https://agentmods.dev/skills/sumitaich1998/opendate/conversation-recovery"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/conversation-recovery/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/sumitaich1998/opendate/conversation-recovery"><img src="https://agentmods.dev/badge/skills/sumitaich1998/opendate/conversation-recovery.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 | $0.00030 | $0.00589 |
| Opus 5 | $0.00015 | $0.00295 |
| Sonnet 5 | $0.00006 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
conversation-recovery 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversation recovery
Every good conversation has a wobble — a joke that didn't land, a topic that fell flat, a message that read wrong. Recovery is the skill of resetting the energy without making the wobble a Whole Thing.
Diagnose first
What kind of dip is it?
- Flat reply (short, low-energy): the topic may be stale, or they're busy.
- Misfire (your joke/comment landed badly): a light, genuine reset is owed.
- Sensitive topic (you hit a nerve): acknowledge, soften, give space.
- Withdrawal (clearly pulling back): respect it — this hands off to
consent-and-safety's back-off rule, not more recovery attempts.
Recovery moves
- For a flat reply: change lanes. Drop the dying topic and open a fresh, lighter one with a specific hook. Don't ask "you ok?" — just bring better energy.
- For a misfire: a quick, low-drama acknowledgment beats over-apologizing. "That came out more sarcastic than my heart intended — let me try again" resets it with charm.
- For a nerve: validate and ease off the topic. "Totally fair — didn't mean to poke at that. Tell me something good instead?"
- Reset the tone, then hand back to the right Building skill once energy returns.
Rules
- Don't over-apologize. One light acknowledgment, then move on. Spiraling apologies create the awkwardness they're trying to fix.
- Never get defensive or blame them for not getting the joke.
- Read for genuine disinterest. If recovery attempts aren't landing, that's a signal to back off gracefully, not to try harder. Persistence after disinterest is off-limits.
- Lower the stakes, don't raise them — humor and warmth over earnestness.
Examples
- Flat reply: > "Okay that topic clearly peaked. New question: what's the most unreasonable hill you'll die on, food or otherwise?"
- Misfire: > "Reading that back, the sarcasm dial was set too high — my bad. What I meant was: I'm genuinely impressed."
Output
A single message that resets the energy lightly — acknowledging a misfire only if there was one — and opens an easy, lower-stakes path forward. If disinterest is the real signal, recommend backing off instead.
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 · 60 lines · 30 tokens per session scan A 34f6a2cffe20
conversation-recovery is a skill published in the GitHub repository sumitaich1998/OpenDate (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 589 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
build-bot-funnel
A workflow that turns a written conversation plan into a validated chatbot flow for Telegram, MAX, or Instagram.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
make-a-deck
Slide presentation in HTML.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
subscription-manager
Create and manage scheduled subscription tasks. Use when the user wants to set up recurring reminders, periodic reports, scheduled checks, or any automated tasks that run on a schedule. Supports cron expressions, fixed intervals, and one-time executions.