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-directory-exists-guidancegit 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-directory-exists-guidance)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/memory-directory-exists-guidance"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/memory-directory-exists-guidance/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-directory-exists-guidance"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/memory-directory-exists-guidance.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 | $0.00023 | $0.00422 |
| Opus 5 | $0.00012 | $0.00211 |
| Sonnet 5 | $0.00005 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
memory-directory-exists-guidance 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.
What it actually says
SKILL: Memory Directory Exists Guidance
Domain: context-management
Trigger: Use whenever you plan to write memory files so the agent can assume the directory exists instead of repeatedly running mkdir -p.
Source Pattern: Distilled from reviewed context, compaction, and memory-governance patterns.
Core Method
Guarantee the auto-memory directory exists with a single idempotent mkdir (handled once per session) and prepend every guidance response with the standard instructions (DIR_EXISTS_GUIDANCE and DIRS_EXIST_GUIDANCE) so Claude knows not to rerun filesystem commands that are already satisfied. Log any mkdir failure asynchronously for telemetry but let the tool write operation report the real error to keep the workflow moving.
Key Rules
- Call
ensureMemoryDirExistsbefore prompting the agent to write memory files so the path is settled; the helper already swallowsEEXISTand warns only on genuine failures. - Always echo either
DIR_EXISTS_GUIDANCEorDIRS_EXIST_GUIDANCEwhen summarizing the directory state to the assistant so it stops issuing mkdir commands. - Keep the mkdir call outside the main agent loop (e.g., in init or once-per-session code) so repeated turns do not spawn redundant filesystem operations.
Example Application
When saving a new memory from within the CLI, run ensureMemoryDirExists(memoryDir) at session start, mention DIR_EXISTS_GUIDANCE, and proceed to open the target file without extra mkdirs; this keeps the assistant focused on writing content instead of housekeeping.
Anti-Patterns (What NOT to do)
- Don’t rerun
mkdir -pright before every write; the persistent guidance plus singleton helper avoids redundant logs and permission stumbling blocks. - Don’t treat the guidance text as optional; skipping it results in the CLI repeatedly prompting for directory creation even though the path already exists.
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 · 27 lines · 23 tokens per session scan A 7edf5b9b02dd
memory-directory-exists-guidance is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 422 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.