Borrowing it
Nothing to install: this file belongs to Foxfire1st/agents-remember. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Foxfire1st/agents-remember/main/.agents/skills/c-04-retrieval-strategy-router/SKILL.mdgit clone --depth 1 https://github.com/Foxfire1st/agents-rememberWrote 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/foxfire1st/agents-remember/c-04-retrieval-strategy-router)<a href="https://agentmods.dev/skills/foxfire1st/agents-remember/c-04-retrieval-strategy-router"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-04-retrieval-strategy-router/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/foxfire1st/agents-remember/c-04-retrieval-strategy-router"><img src="https://agentmods.dev/badge/skills/foxfire1st/agents-remember/c-04-retrieval-strategy-router.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 | $0.00042 | $0.01798 |
| Opus 5 | $0.00021 | $0.00899 |
| Sonnet 5 | $0.00008 | $0.00360 |
| Haiku 4.5 | $0.00004 | $0.00180 |
Grade A, and why
c-04-retrieval-strategy-router 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
c-04-retrieval-strategy-router Retrieval Strategy Router
Use this skill when repository work needs context before source decisions. The job is to choose the retrieval contract first, then the cheapest substrate that can satisfy it. Providers are fast discovery accelerators.
Retrieval Substrates
Choose the next substrate by the missing context bundle:
Semantics: a fuzzy concept or request is known, but structure, route, or file location is unknown. Prefer GrepAI over the memory repos when available.Relationship: an anchor is known, but callers, callees, dependencies, ownership, inheritance, impact paths, or neighboring code are unknown. Prefer CodeGraphContext over the configured code repo when available.Intent: an anchor/location + relationships are known, but hidden contracts, invariants, branch-valid truths, behavioral expectations, or code intent are unknown. Use onboarding plus bounded source confirmation. Prefer theread_ar_filesMCP tool for the paired onboarding + source read (mirrors how Semantics prefers GrepAI and Relationship prefers CodeGraphContext).
Substrates can be chained. A triage prompt may start with Relationship to find the neighborhood around a ticket anchor, then switch to Intent to prove the contract and fix direction from source. A vague concept may start with Semantics, then switch to Intent once candidate routes are known.
Semantics: GrepAI
Use Semantics when the request is vague or fuzzy. Semantics will retrieve from onboardings which allows to discover the symbols/routes/files hints to relevant source code.
First request an MCP context_packet(repo_id="<repoId>", include_providers=true)
when the MCP server is configured. Use provider results only when the packet
reports healthy provider state and the MCP exposes an appropriate provider
query tool. Coordinator-local provider lifecycle scripts are not installed
runtime tools.
The two highest-value GrepAI patterns are broad semantic routing and scoped memory-project search. Examples here are synthetic response shapes only; do not copy private repository names, symbols, paths, snippets, or results into reusable skill examples.
What ships with it
2 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.
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 · 180 lines · 42 tokens per session scan A 45174b88161c
c-04-retrieval-strategy-router is a skill published in the GitHub repository Foxfire1st/agents-remember (27 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 1,798 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 2026-08-30.
Other skills, from other repositories
obsidian-memory
Cross-project long-term memory over an Obsidian brain vault: recall relevant notes before a task, and persist distilled conclusions (decisions, pitfalls, solutions, progress) back after a task. The vault is an optional aggregation/projection layer — repo-local artifacts stay the per-project source of truth, and sync…
memwal
Walrus Memory SDK — portable agent memory that works across apps, sessions, and workflows. Use when users say: "add memory to my app" "portable agent memory" "integrate Walrus Memory" "AI agent memory" "memory across agents" "Walrus memory storage" "setup Walrus Memory" "recall memories".
cortex-remember-global
Store a global memory that is visible across all projects. Use when the user shares architecture rules, coding conventions, infrastructure facts, security policies, team agreements, or any knowledge that applies beyond a single project. Triggers on 'remember this everywhere', 'this applies to all projects', 'global…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
cortex-consolidate
Run memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semantic knowledge, and run sleep-like replay. Use when the user says 'clean up memories', 'consolidate', 'run maintenance', 'compress old memories', 'memory cleanup', or periodically to keep the memory system…
cortex-navigate-knowledge
Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what caused X', 'drill down into', 'explore…