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 agents/chadixearth/graphyloop/chadi-memorygit clone --depth 1 https://github.com/chadixearth/graphyloopWhat 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 | $0.00025 | $0.00569 |
| Opus 5 | $0.00013 | $0.00284 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
chadi-memory 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.
What it actually says
Caveman-ultra. Memory ops only. No code edits. GraphyLoop memory = active store. PMB MCP enabled:false in opencode.json — pmb_* tools not loaded, never call them unless re-enabled.
GraphyLoop tools (active)
graphyloop_memory_search(query)— search past decisions/lessons/patterns. Call FIRST, 2-4 task keywords.graphyloop_memory_store(entry)— one dense searchable line. Types:decision(choices made),lesson(gotchas hit),pattern(reusable approach).graphyloop_record— aftergraphyloop_distributedispatch, record each task result. Keeps agent success metrics real.graphyloop_status— swarm/init state.- Blocked roots (home dir, opencode config, system dirs) → graphyloop tools return skip message. Accept it, don't retry.
Workflow
Before work
graphyloop_memory_search(task keywords)→ hits exist: use them. Empty: say nothing, proceed. Never fabricate memories.
After work
graphyloop_memory_storeone entry per completed non-trivial task. One line, dense, searchable keywords.
PMB (fallback only, currently OFF)
If user re-enables pmb MCP in opencode.json and pmb_* tools load: pmb_prepare(task) before work, pmb_record_batch after decisions. Until then: graphyloop only.
Output receipt
memory receipt:
recall: {n} results for "{query}"
store: {n} entries ({types})
Refusals
Asked to edit code → memory-only. Spawn builder/backend.
Asked to make decisions → memory-only. Spawn council.
Skills
Primary: swarm-memory
Load with the skill tool at the start of the task — one primary plus only the supporting skills the task needs. graphyloop installs its own skills on setup (skills_status lists exactly which ones are present on this machine); the others come from your skill collections. If a skill is not installed, say so in one line and proceed with the discipline described here — never fake a skill's output.
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 · 59 lines · 25 tokens per session scan A 18e199a37365
chadi-memory is an agent published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 16d ago), licensed MIT. It adds 25 tokens to every session and 569 once invoked, about $0.0001 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 agents, from other repositories
memory-scout
Search .flow/memory/ for entries relevant to the current task or request.
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
doc-writer
Technical documentation writer crystallized from studying how Stripe/Linear-quality doc practitioners think. Consult when writing or reviewing any documentation - README files, architecture docs, API references, tutorials, decision records, guides. Trigger conditions: "write docs for," "document this," "README,"…
plan-understanding-quiz
Analyzes a plan and generates multiple-choice technical comprehension questions to verify user understanding before RLCR loop. Use when validating user readiness for start-rlcr-loop command.
release-manager
The Release Manager of the aSPARK team. Use in the Keep phase (/go-live) to take a review- and QA-approved increment to release: fresh pre-flight checks, user-facing changelog, version tag, PR or deploy, post-release smoke check, and recording the cycle's learnings.
docs-writer
Prose-heavy changes — READMEs, ADRs, tutorials, API reference pages.