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/aipmandy/dna-memory/dna-memory-loopnpx skills add AIPMAndy/dna-memory --skill dna-memory-loopgit clone --depth 1 https://github.com/AIPMAndy/dna-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 | $0.00051 | $0.00670 |
| Opus 5 | $0.00026 | $0.00335 |
| Sonnet 5 | $0.00010 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
dna-memory-loop 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 3d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DNA Memory Loop
Use DNA Memory as the cross-client long-term truth. Treat each client's native history as a transcript source, not as a competing durable memory store.
Before substantive work
You MUST recall before relying on history. Treat a task as history-dependent when it refers to prior work, asks to continue, mentions last time or the same plan, names an existing project or path, or depends on a durable preference, known error, workflow, project state, or open loop.
- Extract one to four distinctive terms from the request, project, error, or expected result.
- Call
memory_recallseparately for each term. Always pass the real client: useclient=codex,client=claude-code, orclient=hermesfor those runtimes. Never invent client or session metadata. Pass the current stable session ID only when the runtime exposes it; otherwise omit session_id instead of using a placeholder. - Deduplicate by memory ID. Inject at most five memories and about 2,000 tokens total.
- Use only relevant results. Current files, processes, remote state, and tests override stale memory.
Skip recall for simple, self-contained work such as translation, current time, one-step formatting, or a command that does not depend on history.
Feedback
- Call
memory_feedback(..., outcome="useful")only when a recalled memory changed or confirmed the work. - Use
outcome="misleading"when a memory sent the task in the wrong direction. - Do not submit feedback for a result that was displayed but not used.
After verification
Call memory_remember only for a durable preference, decision with rationale,
fact, insight, reusable workflow, proven error lesson, project state, or open
loop. Write a compact conclusion with bounded source pointers. Never store a
full transcript, credentials, raw prompts, or large tool output.
When current evidence invalidates an older conclusion, read the older memory
IDs and pass only those exact IDs through supersedes. Never infer replacement
from project or type alone.
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.
- 3d ago First seen · 64 lines · 51 tokens per session scan A fbfd9422a5c7
dna-memory-loop is a skill published in the GitHub repository AIPMAndy/dna-memory (93 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 670 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 2026-08-30.
Other skills, from other repositories
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
imsg
Use imsg to read and send iMessage/SMS via macOS Messages.app.
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.
ax-python-agent
Use when writing Python code with axllm for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.
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.