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/ryanzhao1011/workframe/memory-lognpx skills add ryanzhao1011/workframe --skill memory-loggit clone --depth 1 https://github.com/ryanzhao1011/workframeWhat 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 | $0.00052 | $0.01329 |
| Opus 5 | $0.00026 | $0.00665 |
| Sonnet 5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
memory-log 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/core:memory-log 记忆活动流水
用途
用户显式 /core:memory-log 时执行。Claude 不会自动调用。
回答:最近记忆层发生了什么?谁加了什么?谁降级了什么?哪些纠正进入了高置信记忆?shared 有没有新共识?
输入
- 无参数 → 默认近 14 天
7d/30d→ 窗口shared→ 仅 shared/ 范围<role>→ 仅某个角色
执行步骤
- Read
.claude/workframe-state/events.jsonl,逐行 JSON 解析;跳过__schema__描述行和 malformed 行。 - 按窗口过滤事件:
type ∈ {memory_promoted, memory_decayed, user_correction, memory_migrated}rollback_applied仅在target或source指向.claude/agent-memory/或.claude/workframe-state/memory-index.json时纳入。
- Read
.claude/workframe-state/memory-index.json拿当前 sidecar 元数据;若文件不存在,按空索引{entries:{}}处理,并在输出中提示memory-index.json 不存在,仅展示事件快照,当前状态元数据(protected / provenance)不可用。。 - 展示时优先使用事件自带快照字段:
summary/entry_key/source/age_days/provenance(events 是只追加历史层,早期事件可能带旧的数字型confidence快照字段——按原样展示,不换算、不回写)。sidecar 只用于补充当前仍存在条目的protected/provenance等当前状态,不作为历史事实唯一来源。 - 按时间倒序 + scope 分组输出。
scope优先取事件字段;memory rollback 可从路径.claude/agent-memory/<scope>/...推断,无法推断时归入unknown/。
输出格式
## 📔 记忆层活动(近 <N> 天)
### shared/
- 2026-04-20 [promoted] "研发任务签发仅由 qa 执行" (entry=shared:2026-04-20:研发任务签发仅由qa执行, source=notes.md, protected=true)
### pm/
- 2026-04-22 [decayed] "旧的 baseline 路径" (entry=pm:2026-02-16:旧的baseline路径, age_days=65, provenance=external)
- 2026-04-18 [promoted] "自迭代走 proposal 闭环" (entry=pm:2026-04-18:自迭代走proposal闭环)
### dev/
- 2026-04-21 [migrated] "构建脚本必须在仓库根执行" (entry=dev:2026-04-21:构建脚本必须在仓库根执行, source=auto-memory, from_ref=build-script-root-only.md)
- 2026-04-19 [correction] "不要 mock 数据库" (entry=dev:2026-04-19:不要mock数据库, protected=true)
- 2026-04-17 [rolled-back] dev/MEMORY.md → 回滚至 logs/librarian-snapshots/2026-04-15/10-30-dev-MEMORY.md
示例的三条纪律,照抄即合规:组内按日期倒序(与步骤 5 一致);所有条目落在同一窗口内(上例跨 04-17~04-22,任何 ≥7d 的窗口都自洽——decayed 那条的 entry 日期是条目创建日,可以早于窗口,age_days 由它与事件日之差算得);示例值一律虚构通用,不写任何真实项目的条目内容或文件名。
[migrated] 与 [promoted] 展示上要能区分:前者是跨 scope 搬迁(source 指向另一个记忆域),后者是同域内 notes 提升(source 是 notes.md)。搬迁事件带 from_ref,展示时一并给出,否则读者无法回答「它原来在哪」。
[rolled-back] 没有 entry——回滚的对象是整个文件而非单条,故格式为 <文件> → 回滚至 <快照路径>。
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 · 68 lines · 52 tokens per session scan A 4bb03ff00cd9
memory-log is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 15d ago), licensed MIT. It adds 52 tokens to every session and 1,329 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 skills, from other repositories
check-understanding
Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or /check-understanding .
find-your-level
Interactive quiz that maps your AI/ML knowledge to a starting point in the 260-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
eval-hooks
Audit Claude Code hooks defined in settings.json files for validity, performance safety, and correctness. Resolves each command against the filesystem, checks exit-code strategy for blocking hooks, flags missing timeouts, and reviews interactive vs async patterns. Use when setting up hooks for the first time…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.