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 memory-entrypoint-with-index-disciplinegit 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/memory-entrypoint-with-index-discipline)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/memory-entrypoint-with-index-discipline"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/memory-entrypoint-with-index-discipline/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/memory-entrypoint-with-index-discipline"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/memory-entrypoint-with-index-discipline.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 | $0.00031 | $0.00493 |
| Opus 5 | $0.00015 | $0.00246 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
memory-entrypoint-with-index-discipline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Memory Entrypoint With Index Discipline
Domain: context-management
Trigger: Use whenever you’re writing to MEMORY.md so the index stays readable and never exceeds terminal-safe length budgets.
Source Pattern: Distilled from reviewed context, compaction, and memory-governance patterns.
Core Method
Treat MEMORY.md as an index rather than a content store: truncate entries when the line cap or byte cap is reached, issue a warning in place of the dropped detail, and point each entry to a dedicated per-topic file that holds the richer memory frontmatter. Keep the truncation routine deterministic by trimming to 200 lines, then to the last newline before 25 000 bytes, so future reads know exactly what the policy will display.
Key Rules
- Always stop counting entries once you hit
MAX_ENTRYPOINT_LINES; avoid writing new lines beyond the cap and instead move the extra detail into a${ENTRYPOINT_NAME}entry that links to another file. - After trimming, append a warning that mentions which limit fired (
lines,bytes, or both) and hints to keep entries under ~200 characters per line. - Never add content directly to
MEMORY.md; each entry should be one line in the form- [Title](file.md) — one-line hookreferencing a dedicated memory file. - Keep the index a short sentinel that signals the existence and freshness of the memory; save details only in files that the agent can Read or Write when needed.
Example Application
If a user asks you to remember their quarterly OKR planning, add a single hook line to MEMORY.md that links to okr.md and let that file carry the context, while the entry keeps MEMORY.md under 200 lines so the prompt cache never truncates the index unexpectedly.
Anti-Patterns (What NOT to do)
- Don’t append long paragraphs or copies of the memory content directly into
MEMORY.md; doing so triggers truncation every time and loses context visibility. - Don’t continually extend
MEMORY.mdbeyond the caps; once a limit is hit, move future info to a new file instead of letting the file grow uncontrolled.
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.
- 6d ago First seen · 28 lines · 31 tokens per session scan A 603eb4d203f2
memory-entrypoint-with-index-discipline is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 493 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 2026-09-03.
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.