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 ychampion/cskill-agents --skill relevant-memory-selection-by-headergit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/relevant-memory-selection-by-header)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/relevant-memory-selection-by-header"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/relevant-memory-selection-by-header/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/ychampion/cskill-agents/relevant-memory-selection-by-header"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/relevant-memory-selection-by-header.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 | $0.00027 | $0.00427 |
| Opus 5 | $0.00014 | $0.00214 |
| Sonnet 5 | $0.00005 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
relevant-memory-selection-by-header 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 7d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Relevant Memory Selection By Header
Domain: memory-selection Trigger: Apply whenever you have a query and a directory of memory files; reuse this method to pick up to five headers whose descriptions best match the prompt. Source Pattern: Distilled from reviewed memory-header ranking and selective context-injection implementations.
Core Method
Scan the memory directory for file headers, build a compact manifest of filename and description pairs, and ask a constrained ranking model to choose the most relevant entries for the current query. Validate the returned filenames against the scanned manifest so hallucinated results are dropped safely. Return the selected paths plus enough metadata to load or rank them later, and record that the selector ran even if it picked nothing.
Key Rules
- Always filter out filenames already surfaced in prior turns before asking the assistant; otherwise you waste the 5-slot budget on repeats.
- Include recent-tool context so the selector avoids re-suggesting materials that are already active while still surfacing missing warnings or gotchas.
- Guard the schema parsing step: the side query must return a JSON object with
selected_memories(array of strings); drop any entries not matching the scanned filenames. - Even if the assistant returns nothing, record that the selector ran (e.g., via telemetry) so metrics distinguish “ran but picked none” from “never ran”.
Example Application
When answering a question about an old API and you have dozens of memory files, run the manifest-ranking loop to surface only the few headers whose descriptions signal genuine warnings or relevant history, then inject only those paths back into the main context.
Anti-Patterns (What NOT to do)
- Don’t rely on keyword matching alone; a manifest plus constrained ranking pass avoids many of the false positives that naive heuristics create.
- Don’t include already-loaded headers again; it wastes the limited slot budget and makes the assistant revisit stale files.
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.
- 7d ago First seen · 29 lines · 27 tokens per session scan A 3bfa801069f6
relevant-memory-selection-by-header is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 427 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
ackit-context-optimization
Build budgeted context packs and trim instruction bloat for coding agents.
chain
Inject the 3 most recent session IDs for the current workspace into the prompt before Claude responds. Use when starting work and wanting recent session context.
context-efficient-coding
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
k-knowledge
Instructions for recording stable project facts in AGENTS.md or a project map. AGENTS.md is a file that stores guidance for coding agents.