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 skills add maxbaluev/accreted-intelligence --skill framesgit clone --depth 1 https://github.com/maxbaluev/accreted-intelligenceWrote 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/maxbaluev/accreted-intelligence/frames)<a href="https://agentmods.dev/skills/maxbaluev/accreted-intelligence/frames"><img src="https://agentmods.dev/badge/skills/maxbaluev/accreted-intelligence/frames/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/maxbaluev/accreted-intelligence/frames"><img src="https://agentmods.dev/badge/skills/maxbaluev/accreted-intelligence/frames.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 | $0.00029 | $0.00227 |
| Opus 5.5 | $0.00012 | $0.00091 |
| Sonnet 5.5 | $0.00006 | $0.00045 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
frames 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.
What it actually says
frames
Routing sugar over the two MCP verbs — no logic lives here.
- List the queue:
acc frames(CLI, read-only observation). - For each open/waiting frame: read its typed hole + retrieved context, deliberate,
then submit via
acc_act(runtime="continue", input={"frame_id": ..., "submit_token": ..., "proposal_text": ...}). - End
proposal_textwithPREDICT: <0.00-1.00> <why>; acc strips that line before the owner sees it and uses it to calibrate the Work Model against later outcomes. - An identical duplicate submit replays the cached result — resubmitting is safe.
- Surface each resolution's
commitmentid and cited[ids]; drain the queue fully before taking new work — checkpointed frames are work headless runs saved for you.
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 · 19 lines · 29 tokens per session scan A 12414a333e7f
frames is a skill published in the GitHub repository maxbaluev/accreted-intelligence (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 227 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
memory
Project memory powered by Hippo. Use when starting a session, after learning something, after hitting an error, or when the user mentions memory/remember/recall. Auto-invoked at session start.
plur-create-engrams
Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
honcho-integration
Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.
verify
Build, launch, and drive a local Honcho stack to verify a change at its runtime surface (the /v3 HTTP API and the deriver queue). Use when verifying a diff or confirming a change works in the running app.