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 commands/jscott3201/aionforge-memory/memory-bootstrapgit clone --depth 1 https://github.com/jscott3201/aionforge-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 | $0.00015 | $0.00548 |
| Opus 5 | $0.00008 | $0.00274 |
| Sonnet 5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
memory-bootstrap 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.
How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aionforge Memory Bootstrap
Project: $ARGUMENTS
Run the memory-bootstrap procedure once for this project: turn an empty store into a useful substrate so the next session recalls real context instead of starting cold. It is idempotent — recall before writing and re-running updates rather than duplicates.
Procedure
- Confirm the user wants a bootstrap, and check
server_statusif the MCP connection is uncertain. If it is unavailable, say so and stop. - Resolve identity once: prefer
AIONFORGE_AGENT_ID; otherwise use the stable agent UUID from the user or project instructions. Ask once if none exists — do not silently mint a throwaway namespace.capturetakes the bare UUID; recall and work tools takeagent:<uuid>. - Recall first (
searchfor existing conventions/decisions,work_queryfor an existing backlog) so re-runs seed only the gaps;supersedesan existing fact instead of duplicating it. - Gather ground truth from the repo (README, docs, CI config, dependency manifests) and the user. Seed only verified facts — never invented ones.
capturethe durable conventions (dev workflow, branch/merge model, CI gates, coding standards, review norms) and the key architecture decisions and product direction — one focused record each,role: assistant, higher trust (e.g.trust: 0.9) for curated foundational facts.- Query before creating the backlog: work items have no dedup or supersede, so
work_query(filterlevel: epic, match titles in the results) for an existing epic first. Create theepiconly if absent, then add the missing initialtaskchildren viaparent_idunder it. Tasks are work items, not memory episodes. - Optionally seed cross-cutting facts into a
team:<name>namespace if the user authorizes that scope; default to private otherwise. - Verify:
searchthe seeded topics back andwork_querythe backlog to confirm they return. Summarize the categories covered and the work-item ids.
Guardrails
- Never store secrets, credentials, private keys, or raw tokens — in memories or work items.
- Capture only verified facts from the repo or the user; do not seed speculation.
- Widen to a team scope only when the host or user explicitly grants it.
- If the user does not want a bootstrap, do not run it.
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 · 29 lines · 15 tokens per session scan A 36a5765095e3
memory-bootstrap is a command published in the GitHub repository jscott3201/aionforge-memory (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 548 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 commands, from other repositories
save-memory
You are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared.
bootstrap-memory
RUN { git ls-files; git ls-files --others --exclude-standard; } 2>/dev/null | sort -u | xargs wc -l 2>/dev/null | sort -rn | head -150 READ README.md.
pensyve
Route explicit Pensyve memory requests through the bundled MCP server; supports recall, remember, observe, inspect, status, review, forget, and mention-style guidance.
recall
Search Pensyve memory by semantic similarity and text matching.
using-pensyve
Show available Pensyve memory tools, skills, and commands.
consolidate
Run memory consolidation to promote, decay, and archive memories.