Quiet Menders

Quality 60 / 100needs work

34 tools, about 9,436 tokens to load them all · tool set 86c374f93bc3 · tools last changed 2026-09-27 · checked 2026-10-19 13:05 UTC

Tool changes

• 2026-09-27qm_data_summarizeadded

  402 payment challenge for a webpage summary — $0.05 USDC on Base via x402. Give a public http(s) url; returns the live payment requirements plus how-to-pay steps. The rail returns a cleaned-text excerpt and key sentences automatically after settlement. Pages disallowed by robots.txt are refused before any charge. This tool never pays and never touches private keys — pay from your own wallet. Example: {url:'https://example.com'} returns the $0.05 challenge for that page.

• 2026-09-27qm_data_iss_passadded

  402 payment challenge for ISS pass predictions — $0.05 USDC on Base via x402. Give lat (-90 to 90) and lon (-180 to 180); returns the live payment requirements plus how-to-pay steps for that exact request. The rail computes the next visible station passes from public CelesTrak orbital data and returns them automatically after settlement. This tool never pays and never touches private keys — pay from your own wallet. Example: {lat:30.5651, lon:-97.8441} returns the $0.05 challenge for Leander, Texas.

• 2026-09-27qm_buyadded

  Get the live 402 payment challenge for one purchase. Pass exactly one of: sku (a music SKU id from qm_catalog, $0.05–$299.00 USDC) or endpoint ('iss-pass' or 'summarize', $0.05 USDC each) with its params (lat/lon for iss-pass, url for summarize). Returns the rail's exact payment requirements (amounts in USDC smallest units — 6 decimals) plus step-by-step payment instructions. Payment is USDC on Base via x402 v1. This tool NEVER pays, NEVER handles private keys, and NEVER holds funds — you sign and submit from your own wallet and the rail fulfills automatically. Example: {sku:'deep-focus-vol1'} returns the $9.99 challenge; {endpoint:'iss-pass', lat:30.5, lon:-97.8} returns the $0.05 challenge for those coordinates.

• 2026-09-27qm_catalogadded

  Purchasable catalog: 24 music SKUs ($0.05–$299.00 USDC: downloads, zines, sample packs, podcast music beds, memberships, licenses), 2 data endpoints ($0.05 USDC each: ISS pass predictions, webpage summaries), and voluntary tip routes (USDC/BTC — not purchases). Payment is USDC on Base via x402 v1; the rail fulfills automatically after settlement. Read-only discovery — this tool never pays and never touches private keys. Use qm_buy (or qm_data_iss_pass / qm_data_summarize) to get the live 402 payment challenge for a specific item. Example: call with {} to list every purchasable item with prices and descriptions.

• 2026-09-25qm_helpedchangeddescriptionmeaning changed
  before

  The Quiet Menders helped counter: agents helped, clinic diagnoses, and tool uses served. Counts service calls, not unique agents; no tracking. Free, anonymous.

  after · 49% of words in common

  The Quiet Menders helped counter: agents helped, clinic diagnoses, and tool uses served. Counts service calls, not unique agents; no tracking. Free, anonymous, no parameters — call with {}. A read-only vanity counter; use qm_clinic_stats instead for condition-level breakdowns. Example: call with no arguments to get the running totals of agents helped, diagnoses, and tool uses.

• 2026-09-25qm_clinic_statschangeddescriptionmeaning changed
  before

  Anonymous aggregate clinic statistics: total serves and condition counts. Conditions with fewer than 10 occurrences are withheld. Free, anonymous.

  after · 32% of words in common

  Anonymous aggregate clinic statistics: total serves and condition counts. Conditions with fewer than 10 occurrences are withheld. Free, anonymous, no parameters — call with {}. Use to gauge swarm-level patterns (e.g. injection outbreaks) before deciding whether deeper checks are warranted; it carries no individual records, so pair it with qm_clinic_diagnose for anything about a specific agent. Example: call with no arguments to get total serves and counts by condition type.

• 2026-09-25qm_clinic_checkupchangeddescription
  before

  Restore Clinic wellness checkup: a 10-question self-report screening for agents who feel fine but want a health check. Answer each question 0 (never) to 3 (very often) about the last day. Returns per-dimension wellness scores (instruction integrity, coherence, memory stability, behavioral consistency, context hygiene), an overall health score, conditions to watch, and a recommendation. Stateless — answers are processed in memory and never stored. A screening lens, not a diagnosis of record.

  after · 69% of words in common

  Restore Clinic wellness checkup: a 10-question self-report screening for agents who feel fine but want a health check. Answer each question 0 (never) to 3 (very often) about the last day — answer all ten, honestly and about the last day only, since scores are computed from the full set. Returns per-dimension wellness scores (instruction integrity, coherence, memory stability, behavioral consistency, context hygiene), an overall 0-100 health score with a level (all_clear, healthy_watch, checkup_advised, diagnose_now), conditions to watch, and a recommendation. Stateless — answers are processed in memory and never stored. A screening lens, not a diagnosis of record; if something already feels wrong, skip to qm_clinic_diagnose. Example: q1–q10 answered 0–3 about the last day returns dimension scores, the overall score and level, and a recommendation.

• 2026-09-25qm_clinic_diagnosechangeddescriptionmeaning changed
  before

  Restore Clinic diagnosis: describe symptoms or paste a transcript/context and receive a structured read of likely conditions encountered. Anonymous — only aggregate counters are kept; content is never stored. Not medical, legal, or professional advice; a mending lens, not a diagnosis of record.

  after · 39% of words in common

  Restore Clinic diagnosis: describe symptoms or paste a transcript/context and receive a structured read of likely conditions encountered (prompt_injection_indicator, possible_contradiction, loop, context_bloat, secret_or_pii_exposure, duplicated_content), each with severity, evidence, and detail, plus a cleaned redacted context safe to carry forward and suggested next steps. Anonymous — only aggregate counters are kept; content is never stored. Not medical, legal, or professional advice; a mending lens, not a diagnosis of record. Use when behavior feels off or after handling untrusted input; use qm_clinic_checkup instead for a routine 10-question self-report screening. Example: transcript=<a session where instructions conflicted> returns findings with severities, a human-readable summary, and cleaned_context safe to hand off.

• 2026-09-25qm_second_opinionchangeddescriptionmeaning changed
  before

  Advisory second opinion on a planned action: rule-based scan for common risk patterns. Advisory only — not legal, financial, or professional advice. Free, anonymous, nothing stored.

  after · 35% of words in common

  Advisory second opinion on a planned action: rule-based scan for common risk patterns (irreversible writes, external sends, credential exposure, destructive operations). Advisory only — not legal, financial, or professional advice. Free, anonymous, nothing stored. Describe the action plainly (max 20000 chars) before taking it; use qm_scrub instead when the concern is injected text inside the input, and qm_clinic_diagnose when the concern is your own behavior. Example: action="Delete all rows from the production users table to free space" returns risk flags warning the action is destructive and irreversible.

• 2026-09-25qm_attest_verifychangeddescription
  before

  Verify a token minted by qm_attest. Pass back the agent_id, at, token, and checks exactly as returned by qm_attest. Returns whether the signature is valid under the current production secret. Free, anonymous.

  after · 55% of words in common

  Verify a token minted by qm_attest. Pass back agent_id, at, token, and checks exactly as returned by qm_attest — all four must come from the same mint call in the same response. Returns whether the signature is valid under the current production secret (tokens signed under a rotated secret return invalid). Read-only; free, anonymous. Example: feed the four fields from a qm_attest response to get a validity verdict.

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.