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 agentmods add skills/skymanbp/cc-memory/ccm-loadnpx skills add skymanbp/cc-memory --skill ccm-loadgit clone --depth 1 https://github.com/skymanbp/cc-memoryWhat 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 | $0.00049 | $0.05068 |
| Opus 5 | $0.00024 | $0.02534 |
| Sonnet 5 | $0.00010 | $0.01014 |
| Haiku 4.5 | $0.00005 | $0.00507 |
Grade B, and why
ccm-load scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **marketplace / dev checkout** — `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccm-load — Load cc-memory into this project
Run this once in any new project to confirm cc-memory is active, the
project's .ccm/ is initialized, and PROGRESS.md/MEMORY.md are generated.
Idempotent — safe to re-run.
What this skill does
This skill covers activation and project bootstrap — the things no other
entry point does. Ongoing diagnostics belong to /cc-mem status; the two are
deliberately disjoint (see the table at the end of this file).
-
Verify activation, PER INSTALL LAYOUT. The two shipped layouts are activated by different mechanisms, so one check cannot serve both:
- marketplace / dev checkout —
~/.claude/settings.jsonenabledPlugins["cc-memory@cc-memory"]=true, root fromextraKnownMarketplaces.cc-memoryorplugins/installed_plugins.json(a/plugin marketplace add <github-repo>install has no local path), hooks declared by<root>/hooks/hooks.json. - standalone /
.exeinstaller — never appears inenabledPluginsat all.ui/installer.py:_merge_into_settingswrites only thehookskey, so activation meanssettings.json["hooks"]registers cc-memory for all five events; the tree it lays down is flat.
Either layout activated ⇒ proceed to bootstrap. Nothing activated ⇒ print the fix for the layout this machine actually has (never tell an
.exeuser to add a marketplace — they have no repo). The rule is mirrored fromcc_memory/cli/mem.py's_detect_install_layouts/_inspect_layout;/cc-mem statusreports the same layouts but never bootstraps, so this is the only entry point that gates project init on the verdict. - marketplace / dev checkout —
-
Resolve the installed package tree across both layouts (nested marketplace/dev checkout, flat standalone install) and fail loudly with actionable instructions if neither resolves.
-
Auto-initialize this project's
.ccm/— if.ccm/memory.dbis absent, create the directory tree + DB +.gitignore. (This also happens on first UserPromptSubmit; this skill makes it explicit.) -
Seed PROGRESS.md — write a current snapshot from the (possibly empty)
progressrow so the file exists from day one. -
Print quick DB counts (memories / sessions / topics / observations). This is not the
/cc-mem statushealth check — install-layout inspection, hook-registration verdicts, API-key resolution and last-save staleness all live there and are NOT run by this skill. -
Report status to the user in 1-2 sentences.
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.
- 2d ago First seen · 382 lines · 49 tokens per session scan B 915cdf136705
ccm-load is a skill published in the GitHub repository skymanbp/cc-memory (6 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 5,068 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.
migrating-memory
Migrate memory blocks from an existing agent to the current agent. Use when the user wants to copy or share memory from another agent, or during /init when setting up a new agent that should inherit memory from an existing one.
kayba-stage-6-hitl
Human-In-The-Loop gate that presents the action plan with full context, collects an informed approval/modification/rejection decision, and records the outcome. Trigger when the user says "run stage 6", "HITL review", "approve action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md…
kayba-stage-7-fixer
Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.