Borrowing it
Nothing to install: this file belongs to vladm3105/aidoc-flow-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vladm3105/aidoc-flow-framework/dev/.agents/skills/memory-hygiene/SKILL.mdgit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/memory-hygiene)<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/memory-hygiene"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/memory-hygiene/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/vladm3105/aidoc-flow-framework/memory-hygiene"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/memory-hygiene.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 | $0.00046 | $0.01431 |
| Opus 5.5 | $0.00018 | $0.00572 |
| Sonnet 5.5 | $0.00009 | $0.00286 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
memory-hygiene scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory hygiene
Muse project-skill instance — adapted from the canon global skill (
aidoc-flow-claude-agents-config/skills/memory-hygiene/, private). Claude-specific-to-neutral wording mirrorsframework/skills/memory-hygiene/(engine-agnostic adaptation of this same skill). Paths below use<skills-root>= the skills root for your engine (here:.agents/skills/).
Nothing reads the memory store except the loader, so drift is silent and
compounds. Measured on 2026-08-12 across 14 stores and 341 memories: one store
(-opt-data-techtrend-AI-cost-monitoring) had spent six months holding all
of its content inline in MEMORY.md with zero memory files, and three others
carried link or bloat defects. None of it surfaced, because nothing looked.
Resolve the store
SLUG=$(printf '%s' "$PWD" | sed 's#[/_.]#-#g')
MEMDIR=<repo-declared-memory-store>
The slug maps /, _ and . to - — verified against every store on
disk, including …runner-local--work-… (_work) and -opt-data-trading-nexus-v4-2
(v4.2). Case is preserved, not lowercased.
The rule is derived from the directory names, not from harness source, so it
must fail loudly. If $MEMDIR is absent, list <repo-declared-memory-stores>/ and look
for a store whose slug matches before concluding there is none. "Could not
resolve a store for this path" and "this project has no memories" are
different statements and only the second may be acted on.
The slug keys on the session's start directory, not the repo, so one repo can own several project directories. Counts here are per-directory.
Run it
python3 <skills-root>/memory-hygiene/lint.py "$MEMDIR" --brief # one line, read-only
python3 <skills-root>/memory-hygiene/lint.py "$MEMDIR" # full report, exit 1 on any violation
python3 <skills-root>/memory-hygiene/lint.py "$MEMDIR" --fix # deterministic repairs only — see the gate below
What it checks
| Check | Defect | Remedy |
|---|---|---|
MEMORY.md is an index |
prose, tables or code where one-line pointers belong | manual — never --fix |
| index exists | memories on disk with no MEMORY.md |
reindex |
| index 1:1 with files | orphan files · stale pointers · duplicates | reindex |
[[links]] resolve |
dangling wiki-links; unambiguous ones are auto-fixable | --fix, else manual |
name == filename stem |
frontmatter drifted from the filename | --fix |
| no slug titles | index titles that are filenames rather than prose | reindex / retitle |
| hook text ≤ 300 chars | an index line that has become the memory | compact |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 110 lines · 46 tokens per session scan A 46c29a462bb0
memory-hygiene is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,431 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-28.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…