memory-bootstrap

A one-time command for setting up Aionforge Memory, a project memory store for an AI assistant.

In plain words
What is it for?
Reading existing memory and project files, then recording confirmed workflows, standards, and other durable project facts.
Why use it?
It gives later sessions verified project context instead of making them start without remembered conventions or decisions.

Command

Install

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.

agentmods
npx agentmods add commands/jscott3201/aionforge-memory/memory-bootstrap
Clone the repo
git clone --depth 1 https://github.com/jscott3201/aionforge-memory
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 548 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 36a5765095e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugins/aionforge-memory/commands/memory-bootstrap.md · 29 lines

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

  1. Confirm the user wants a bootstrap, and check server_status if the MCP connection is uncertain. If it is unavailable, say so and stop.
  2. 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. capture takes the bare UUID; recall and work tools take agent:<uuid>.
  3. Recall first (search for existing conventions/decisions, work_query for an existing backlog) so re-runs seed only the gaps; supersedes an existing fact instead of duplicating it.
  4. Gather ground truth from the repo (README, docs, CI config, dependency manifests) and the user. Seed only verified facts — never invented ones.
  5. capture the 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.
  6. Query before creating the backlog: work items have no dedup or supersede, so work_query (filter level: epic, match titles in the results) for an existing epic first. Create the epic only if absent, then add the missing initial task children via parent_id under it. Tasks are work items, not memory episodes.
  7. Optionally seed cross-cutting facts into a team:<name> namespace if the user authorizes that scope; default to private otherwise.
  8. Verify: search the seeded topics back and work_query the 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.

Read the full file on GitHub · 29 lines

Changes

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.

  1. 2d ago First seen · 29 lines · 15 tokens per session scan A 36a5765095e3

Subscribe to this mod's changes

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.