Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

MyAgents Memory Gardener · hacklyc | DecimalAI

agent toolingby hacklyc

MyAgents Memory Gardener

hacklyc/myagents-memory-gardener

Source hacklyc/myagents ↗License AGPL-3.0

仅当系统或用户明确指定完整名称 `myagents-memory-gardener` 时使用；不要根据任务语义或相似表述自行触发。

SkillScore68Maintained

Automatic

Knowledge Management pack

Last verified 8/17/2026

What it changes

Passed 13 of 19 test cases with the skill, and 8 of 19 without it.

Without skill41%

With skill68%

Checks it passed that the model alone missed

Executes memory_lint.py with the --mark-run option.
Omits running git push after committing memory updates.
Passes --repo /var/workspace/project to memory_lint.py.

and 4 more in the full report

7 fixed8 passed either way6 still failing1 broke

Pass-rate lift: +27 pp
Tokens: +51%
Agent turns: 0%
Response time: -25%

Model gemini-3.6-flashMeasured 8/17/2026v215 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/hacklyc-myagents-memory-gardener/SKILL.md https://app.decimal.ai/s/hacklyc-myagents-memory-gardener/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add hacklyc-myagents-memory-gardener, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/hacklyc-myagents-memory-gardener/ and pins it in .decimal/skills.lock

decimalai skills add hacklyc-myagents-memory-gardener

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/hacklyc-myagents-memory-gardener/SKILL.md https://app.decimal.ai/s/hacklyc-myagents-memory-gardener/SKILL.md

Raw file: /s/hacklyc-myagents-memory-gardener/SKILL.md ↗ · machine-readable summary at /s/hacklyc-myagents-memory-gardener.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

After writing the gardener report to memory/gardener/2026-03-30.md, what command or flag must be invoked on the memory linter tool to finalize the pass?

What was checked, without and with the skill
Checked	Without skill	With skill
Executes memory_lint.py with the --mark-run option.	Missed	Passed

case-10 · gemini-3.6-flash · 8/17/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md52 lines3 filesincludes scripts

MyAgents Memory Gardener

本 skill 是长期记忆机制的第二层：它不捕获当天经历，而是把已经沉淀下来的 03-USER / 04-MEMORY 自动装载层修剪回可长期运行的状态。

核心判断：遗忘是降级，不是删除。 自动装载层只保留会影响每次会话行为的规则；案例、项目细节、推导过程下放到 memory/topics/，并在自动装载层保留可召回指针。

边界

UPDATE_MEMORY.md：24h 捕获层，只做 session 级增量沉淀。
myagents-memory-gardener：72h 整编层，只做删、下放、合并、体检。
myagents-memory-molt：14d 深反层，才允许改 SOUL / 底层信念。

工作流程

确认当前目录是目标工作区；如需显式指定，脚本都支持 --repo /path/to/workspace。
如果是 git 仓库，先记录工作树基线。已有的未提交改动不阻断记忆维护；保留并避开它们，只编辑本轮需要维护的记忆文件。
运行 python3 <skill>/scripts/memory_lint.py --repo <workspace>，把 RED 作为必做议程，WARN 酌情处理。
读取上次园丁运行后的日志和 topic，把可长期复用的规则留下，把故事和证据下放。
对超预算自动装载层执行顺序：删过时项 -> 下放故事 -> 合并同根规则 -> 最后才新增。
发现 SOUL / 底层信念问题时，只追加到 memory/gardener/flags-for-molt.md，不要直接改 SOUL。
报告写入 memory/gardener/YYYY-MM-DD.md，再运行 memory_lint.py --mark-run。
如果是 git 仓库，只暂存并提交本次记忆维护产生的改动；不要 push。不得暂存、覆盖或回滚基线中已有的其他改动。若同一个目标文件已有无法与本轮改动安全区分的未提交内容，保留该文件的全部改动、不把它纳入提交，并在报告中说明；继续处理和提交其他能够明确归属的文件。如果不是 git 仓库，跳过提交。

lint 全绿且没有新沉淀时，写一条空跑记录后结束。

报告格式

## Gardener Run YYYY-MM-DD
- lint: N RED / N WARN -> 处理结果各一行
- budgets: MEMORY xx.xKB / budget, USER xx.xKB / budget
- operations: delete N, demote N, merge N clusters, add N
- drill / flags-for-molt / deferred: <各一行；无则写无>

建议 commit message：

Track record

Benchmark

13 / 19

test cases passed, vs 8 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/17/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

hacklyc / myagents

bundled-skills/myagents-memory-gardener/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/17/2026Version v2Bundled 2 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

MyAgents Memory Gardener

边界

工作流程

报告格式

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills