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/jscott3201/aionforge-memory/memory-capturenpx skills add jscott3201/aionforge-memory --skill memory-capturegit clone --depth 1 https://github.com/jscott3201/aionforge-memoryWrote 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/jscott3201/aionforge-memory/memory-capture)<a href="https://agentmods.dev/skills/jscott3201/aionforge-memory/memory-capture"><img src="https://agentmods.dev/badge/skills/jscott3201/aionforge-memory/memory-capture.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00658 |
| Opus 5 | $0.00026 | $0.00329 |
| Sonnet 5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
memory-capture 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 4d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Capture
Requires an enabled Aionforge Memory MCP server.
Use this skill to make useful work durable. Prefer several focused captures over one sparse summary.
Capture as you go, not at the end. The moment a durable fact lands — a decision made, a fix verified, a release or CI state change, a user preference learned, an approach rejected — write it. Batching to the end loses the precise context, and a context compaction can discard it first.
Route To The Right Node
capture writes a memory episode: a durable fact that decays over time and can be superseded or forgotten. Two things are not episodes:
- A task, blocker, TODO, or plan step is a work item, not a memory. Use the
work-trackingskill (work_create→work_advance); work items persist and are status-tracked. - There is no "note" you store directly. Notes are derived by
consolidatefrom episodes — never written by hand. If a "note" tempts you, it is either a durable fact (capture) or a thing to do (work_create).
Procedure
- Write memory when the user asks, when project instructions grant standing permission, or when a substantial task produces durable facts future agents should know.
- Resolve the writer identity once: prefer
AIONFORGE_AGENT_ID; otherwise use the stable UUID supplied by the user or project instructions. - Capture one fact, decision, outcome, or handoff per call. Include project, date when useful, evidence, current branch/PR/release ids, and validation status.
- Use
role: assistantfor session summaries and decisions; userole: eventfor external project events. - If the memory corrects or replaces an older memory, pass the older id as
supersedes. - Preserve receipt ids in the final answer when follow-up audit, forget, or supersession is likely.
- After several writes, check
consolidation_status; runconsolidateonly when tool approval policy and user/project rules allow mutating derived memory.
What To Capture
- User preferences and standing workflow rules.
- Decisions, corrections, and why they changed.
- Durable project facts, release status, CI state, and validation outcomes.
- Failed approaches, known hazards, and reusable recovery patterns.
- Handoffs with branch, PR, commit, remaining work, and caveats.
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.
- 4d ago First seen · 48 lines · 52 tokens per session scan A 22843b2bac4b
memory-capture is a skill published in the GitHub repository jscott3201/aionforge-memory (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 658 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 2026-08-31.
Other skills, from other repositories
brain-bitemporal
How to query the INITE Brain knowledge graph across time — the asOf parameter, validFrom/validUntil semantics, reading retracted facts, and the memorydiff "what changed between two cursors" surface. Use when the user's question has a temporal dimension ("on X date", "before Y", "what's new since last conversation").
brain-recall
Recall everything brain knows about one specific entity — current profile, full bitemporal timeline, graph neighbours, and unresolved disagreements. Use when the user names a person/company/thing and asks "tell me about them", "what's their history", or "what do we still disagree about?". For a single-shot LLM…
memory-review
Memory hygiene audit -- finds stale facts, contradictions, low-confidence entries, and consolidation candidates in Pensyve memory. Use periodically to maintain memory quality.
session-memory
End-of-session memory capture -- classifies session signals using a tiered taxonomy and stores confirmed items via Pensyve. Use when ending a work session or when the user wants to capture what was learned.
memory-informed-refactor
Pre-refactor context briefing -- loads relevant prior decisions, failures, and pitfalls from Pensyve memory before refactoring a module. Use before any refactor to avoid repeating past mistakes.
memory-informed-debug
Debug with working memory -- before diagnosing, recall prior root causes and known-good diagnostic procedures; when a root cause is confirmed, capture it immediately. Use whenever debugging a non-trivial failure.