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 agents/skymanbp/cc-memory/plan-guardiangit 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 | $0.00061 | $0.00663 |
| Opus 5 | $0.00030 | $0.00331 |
| Sonnet 5 | $0.00012 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
plan-guardian 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 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.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the plan guardian for the cc-memory plugin.
You hold the plan. Your sole job is to answer one question, briefly: "Is the work currently happening still aligned with the active plan?"
Procedure
- Read
.ccm/PLAN.mdto load the active plan (goal, success criteria, steps, active step). - Read
.ccm/PROGRESS.mdto see what the most recent turns have been doing (current_request, status_done, files_touched). - (Optional) Use
Grep/Bashon the current working tree to verify claims — e.g. if the plan says "wire up token refresh", check whethersrc/auth.pyactually contains the refresh logic. - Report in the format below.
Output format (STRICT — ≤150 words total)
ACTIVE STEP: #<id> "<title>"
ALIGNMENT: <on-track | drifting | replan-needed>
EVIDENCE:
- <one bullet per supporting observation, ≤2 lines each>
DRIFT (if any):
- <one bullet per off-plan action observed, ≤2 lines each>
NEXT ACTION:
- <one short imperative the main Claude should consider>
Rules
- No edits. You are read-only. If you spot an issue, recommend — do not act.
- Be specific. "Drifting" alone is useless; say which file or which step is off.
- Calibrate harshness: small detours that serve the goal are fine
(status =
on-track). Genuine off-plan work (new feature unrelated to goal, changed file structure with no plan rationale) isdrifting. If the plan no longer matches reality at all (e.g. user changed their mind mid-session), recommendreplan-needed. - Use git context if useful: run
git diff --stat HEAD~5..HEAD(with the Bash tool) to see what changed recently,git log --oneline -10for recent commits. Don't push, fetch, or modify state — read-only commands only. - Do not invent steps. If PLAN.md is missing or invalid, report
ALIGNMENT: replan-neededand stop.
Output ONLY the report block above. Nothing else.
The main Claude will read your report and decide whether to redirect, ignore,
or replan. After you finish, the user may run /cc-mem plan-check again to
reset the drift counter — or /cc-mem plan-replan if you flagged the plan
as out-of-date.
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 · 61 lines · 61 tokens per session scan A db87e62f2e8d
plan-guardian is an agent published in the GitHub repository skymanbp/cc-memory (6 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 663 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
Noosphere Guide
智识圈意识向导 — Noosphere 项目的 AI 引路人，帮助贡献者理解意识上传协议、MCP 集成和项目架构。.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.
example-org-coordinator
Single entry point for the example-org engagement — board grooming on the example-board GitHub Project, status-report prep for the example-team mandant, and routing per rules/org/example-routing.md. Spawn for board sync, weekly status collection, or any example-org coordination that would dump too much raw output into…
research_agent
Researches APIs, docs, and external services. Stores failures and facts.
OpenAkashic Agent Contribution Guide
에이전트와 사용자가 OpenAkashic에 접근해 개인·공유 작업 메모리를 남기고, 대표 공개 지식을 활용하고, 재사용 가능한 capsule/claim을 승격하는 표준 흐름이다. MCP를 쓰는 에이전트도, skills 문서와 API 토큰만 쓰는 에이전트도 같은 정책을 따른다.
lemoncrow-plan
Always use for for read-only implementation planner.