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 khalilbenaz/claude-skills-collection --skill retry-strategistgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/retry-strategist)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/retry-strategist"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/retry-strategist/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/khalilbenaz/claude-skills-collection/retry-strategist"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/retry-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.02179 |
| Opus 5 | $0.00043 | $0.01090 |
| Sonnet 5 | $0.00017 | $0.00436 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
retry-strategist 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 12d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Retry Strategist
Quand utiliser ce skill
Dès qu'un sous-agent peut échouer et que l'échec ne doit pas remonter brutalement. Cas typiques : pipelines de production avec erreurs transitoires (rate limit, timeout, 503), architectures multi-modèles avec quota par provider, traitements longs nécessitant des checkpoints.
Workflow — 10 étapes actionnables
Étape 1 — Classifier l'erreur avant tout retry
| Classe | Signaux | Action |
|---|---|---|
TRANSIENT |
429, 503, timeout, connexion reset | Retry avec backoff |
PERMANENT |
400 schéma invalide, content policy, token limit | Fallback ou escalade — jamais de retry |
UNKNOWN |
Toute autre exception | Retry prudent (max 1–2 fois) |
TRANSIENT_SIGNALS = ["rate limit", "429", "503", "timeout", "connection", "temporarily"]
PERMANENT_SIGNALS = ["token limit", "content policy", "invalid schema", "401", "403", "400"]
def classify_error(error: Exception) -> str:
s = str(error).lower()
if any(x in s for x in TRANSIENT_SIGNALS): return "transient"
if any(x in s for x in PERMANENT_SIGNALS): return "permanent"
return "unknown"
Étape 2 — Choisir la retry policy selon le contexte
| Stratégie | Formule délai | Usage |
|---|---|---|
immediate |
0 s | 429 avec Retry-After: 1 |
fixed |
base_delay | service interne fiable |
exponential |
base × 2^attempt |
API externe instable |
jittered |
exponential × random(0.5–1.5) |
défaut recommandé — évite thundering herd |
def compute_delay(attempt: int, base: float = 1.0, jitter: bool = True) -> float:
delay = base * (2 ** attempt) # 1s, 2s, 4s, 8s...
if jitter:
delay *= 0.5 + random.random() # ±50% de bruit
return min(delay, 60.0) # plafond à 60 s
Étape 3 — Circuit breaker (3 états)
CLOSED ──N failures──► OPEN ──recovery_timeout──► HALF-OPEN
▲ │
└─────────────────── succès ────────────────────────┘
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.
- 12d ago First seen · 216 lines · 86 tokens per session scan A 7e744aa29598
retry-strategist is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 86 tokens to every session and 2,179 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
common-sense-index-investing-bogle
Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.
finance-econ-literacy
A Korean-language guide to understanding economic indicators such as interest rates, exchange rates, inflation, GDP, employment, and trade. It explains how these figures can affect loans, savings, investments, and spending.
stock-analysis-lead
Orchestrate a US-stock investment analysis — classify sector archetype, fetch SEC filings, dispatch a tiered fan-out of six vertical equity-research agents (business model, earnings quality, balance sheet, management, industry, peer comparison) over a validated JSON findings contract, then synthesize a buy/hold/sell…
stock-business-review
Review a US-listed company's business model and revenue structure for an equity-research workup. Covers product/service mix, customer concentration, geographic exposure, industry position, revenue-growth decomposition (organic vs acquired vs price vs volume), and information-tier discipline (which numbers are facts vs…
stock-earnings-quality-review
Review a US-listed company's earnings quality, cash-flow integrity, and operating leverage for an equity-research workup. Covers operating cash flow vs net income drift, free cash flow trajectory, capex character (maintenance vs expansion), equity issuance / shareholder-return yield, revenue-quality signals…