Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

refresh-rate-card

Étoiles1

Forks0

Mis à jour13 mai 2026 à 18:00

Updates shared/rate-card.json with a new per-model rate table. Validates the proposed update against the existing schema, diffs prices against the current card, and produces a commit-ready diff for human review. Use when: CI nightly job detects a pricing change on Anthropic's published rate page, or when the developer runs /refresh-rate-card after verifying a price change. Do not use at runtime during a Claude Code session — this skill runs in CI or at developer invocation, never inside the observation hot path.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

enchanter-ai

enchanter-ai/pech

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	refresh-rate-card
description	Updates shared/rate-card.json with a new per-model rate table. Validates the proposed update against the existing schema, diffs prices against the current card, and produces a commit-ready diff for human review. Use when: CI nightly job detects a pricing change on Anthropic's published rate page, or when the developer runs /refresh-rate-card after verifying a price change. Do not use at runtime during a Claude Code session — this skill runs in CI or at developer invocation, never inside the observation hot path.
model	sonnet
tools	["Read","Write"]

refresh-rate-card

Preconditions

Fresh rate data is available as structured JSON (provided as argument, not fetched here)
The proposed JSON validates against the schema (see load-rate-card step 2-4)
Not running inside a hook context (refresh is a deliberate developer/CI action)

Inputs

Proposed rate-card JSON: the new values to write
Current card: shared/rate-card.json

Steps

Validate the proposed card's schema (same checks as load-rate-card).
Diff against the current card:
- For each model: compare input_rate and output_rate.
- For each modifier: compare value.
- Summarize changes: {model, field, old_value, new_value, pct_change}.
If any price changes by > 20% in either direction, flag as suspicious_change — require explicit confirmation before writing. Anthropic pricing historically moves by ≤ 10% per change.
Append the current card to state/rate-card-history.jsonl (audit trail of all prior cards).
Write the new card to shared/rate-card.json via atomic temp-rename (@../vis/packages/core/conduct/verification.md § dry-run pattern).
Set _meta.last_verified to today.
Emit pech.rate_card.refreshed with the diff summary.

Success criterion: new card is valid, history is preserved, diff summary emitted. Never overwrite the card without appending history — audit trail is load-bearing for forecasting backtests.

Outputs

Updated shared/rate-card.json
Appended state/rate-card-history.jsonl
Event: pech.rate_card.refreshed with diff

Handoff

CI workflow commits the updated card in a PR. Developer review decides whether suspicious_change flags require reverting.

Failure modes

Code	Scenario	Counter
F10	Overwrite the card without appending history	Hard-fail — atomic rename requires history append in the same operation
F11	Silently pass a > 20% change because the diff looks clean	`suspicious_change` flag is mandatory regardless of visual appearance
F14	Apply a rate change retroactively to old ledger rows	Forbidden — old rows stay at their computed-at-write-time cost; audit trail compares against rate-card-history.jsonl

Plus depuis ce dépôt

même dépôt

check-budget

enchanter-ai/pech

Runs L2 Budget Boundary Detection after each ledger write: increments per-scope counters, compares against ceilings in state/budgets.json, emits pech.budget.threshold.crossed on first crossing of each threshold within each scope-window. Use when: a PostToolUse hook fires and cost-tracker has already written the ledger row. Do not use for forecasting (see forecast-cost) or anomaly detection (see detect-anomaly).

2026-05-131

observe-call

enchanter-ai/pech

Writes a single ledger row for the most recent tool-use call: reads the API response's usage field (authoritative), looks up the model rate in shared/rate-card.json, applies prompt-cache modifiers (1.25× write, 0.1× read), computes billed cost, and appends to plugins/cost-tracker/state/ledger-YYYY-MM.jsonl. Use when: a PostToolUse hook fires for any tool and attribution metadata is available via ENCHANTED_ATTRIBUTION env. Do not use for forecasting (see /pech-forecast → forecast-cost) or for anomaly detection (see budget-watcher/detect-anomaly).

2026-05-131

rate-awareness

enchanter-ai/pech

Token-bucket advisory rate limiter per skill+session. Surfaces runaway tool-call loops in real time before pech/budget-watcher reports them post-hoc. Auto-fires on PreToolUse. Configurable per-skill limits via state/buckets.json. Do not use for cost reporting (see budget-watcher) or for blocking installs (see package-gate).

2026-05-131

rate-shield-awareness

enchanter-ai/pech

OPT-IN BLOCKING token-bucket rate limiter. Pairs with pech-rate-limiter (advisory). When state/rate-policy.json sets enabled:true, this shield blocks (exits 2) any tool call once the active (session, skill) bucket is empty. Reads buckets from rate-limiter's state/buckets.json when present; gracefully degrades when absent. Use when the developer asks why a tool call was rate-blocked, wants to enable or tune the rate policy, or reviews a stderr "rate-shield (BLOCKED)" message. Default disabled. Do not use for advisory-only velocity signals (see rate-limiter) or for cost reporting (see budget-watcher).

2026-05-131

accumulate-pattern

enchanter-ai/pech

Updates per-developer cost-pattern accumulator in state/learnings.json with the current session's observations. Rolls μ and σ per (skill, session_type, model) axis using a slow exponential update (α = 0.05) so one noisy session doesn't skew learned patterns. Exports a cross-plugin-readable snapshot to shared/learnings.json. Use when: PreCompact hook fires (end-of-session or compaction trigger). Do not use during an active session — runtime invocation mid-session would distort the pattern.

2026-04-231

detect-anomaly

enchanter-ai/pech

Runs L3 Z-Score Cost Anomaly detection against the last 30 ledger rows matching the same attribution tuple (plugin, sub_plugin, skill, agent_tier, model). Fires pech.anomaly.detected when |z| > 3, for both spikes and drops. Use when: a PostToolUse hook fires and the ledger row is in place. Do not use when the attribution tuple has fewer than 30 historical matches — emit insufficient_data instead of false-positive anomaly.

2026-04-231

name	refresh-rate-card
description	Updates shared/rate-card.json with a new per-model rate table. Validates the proposed update against the existing schema, diffs prices against the current card, and produces a commit-ready diff for human review. Use when: CI nightly job detects a pricing change on Anthropic's published rate page, or when the developer runs /refresh-rate-card after verifying a price change. Do not use at runtime during a Claude Code session — this skill runs in CI or at developer invocation, never inside the observation hot path.
model	sonnet
tools	["Read","Write"]

refresh-rate-card

Preconditions

Fresh rate data is available as structured JSON (provided as argument, not fetched here)
The proposed JSON validates against the schema (see load-rate-card step 2-4)
Not running inside a hook context (refresh is a deliberate developer/CI action)

Inputs

Proposed rate-card JSON: the new values to write
Current card: shared/rate-card.json

Steps

Validate the proposed card's schema (same checks as load-rate-card).
Diff against the current card:
- For each model: compare input_rate and output_rate.
- For each modifier: compare value.
- Summarize changes: {model, field, old_value, new_value, pct_change}.
If any price changes by > 20% in either direction, flag as suspicious_change — require explicit confirmation before writing. Anthropic pricing historically moves by ≤ 10% per change.
Append the current card to state/rate-card-history.jsonl (audit trail of all prior cards).
Write the new card to shared/rate-card.json via atomic temp-rename (@../vis/packages/core/conduct/verification.md § dry-run pattern).
Set _meta.last_verified to today.
Emit pech.rate_card.refreshed with the diff summary.

Success criterion: new card is valid, history is preserved, diff summary emitted. Never overwrite the card without appending history — audit trail is load-bearing for forecasting backtests.

Outputs

Updated shared/rate-card.json
Appended state/rate-card-history.jsonl
Event: pech.rate_card.refreshed with diff

Handoff

CI workflow commits the updated card in a PR. Developer review decides whether suspicious_change flags require reverting.

Failure modes

Code	Scenario	Counter
F10	Overwrite the card without appending history	Hard-fail — atomic rename requires history append in the same operation
F11	Silently pass a > 20% change because the diff looks clean	`suspicious_change` flag is mandatory regardless of visual appearance
F14	Apply a rate change retroactively to old ledger rows	Forbidden — old rows stay at their computed-at-write-time cost; audit trail compares against rate-card-history.jsonl