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/modeled-information-format/mnemonic/capturegit clone --depth 1 https://github.com/modeled-information-format/mnemonicWhat 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 | $0.00006 | $0.02979 |
| Opus 5 | $0.00003 | $0.01489 |
| Sonnet 5 | $0.00001 | $0.00596 |
| Haiku 4.5 | $0.00001 | $0.00298 |
Grade A, and why
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 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Search first: /mnemonic:search {relevant_keywords}
Capture after: /mnemonic:capture {namespace} "{title}"
Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.
/mnemonic:capture
Capture a new memory to the mnemonic filesystem.
Arguments
<namespace>- Required. Hierarchical namespace path using cognitive triad (prefixed with _ for filesystem disambiguation):- Semantic (facts/knowledge):
_semantic/decisions,_semantic/knowledge,_semantic/entities - Episodic (events/experiences):
_episodic/incidents,_episodic/sessions,_episodic/blockers - Procedural (processes/steps):
_procedural/runbooks,_procedural/patterns,_procedural/migrations
- Semantic (facts/knowledge):
<title>- Required. Human-readable title for the memory--type- Memory type: semantic (default), episodic, or procedural--tags- Comma-separated list of tags--scope- project (default, current project) or org (shared across all projects in organization)--confidence- Confidence score 0.0-1.0 (default: 0.95)--citations- JSON array of citation objects (see format skill for schema)--entity-type- Entity type from ontology (e.g., technology, component, runbook)--entity-id- Custom entity ID (auto-generated if not provided)
Procedure
Step 1: Parse Arguments
NAMESPACE="${1:-decisions}"
TITLE="${2:-Untitled Memory}"
TYPE="${TYPE:-semantic}"
SCOPE="${SCOPE:-project}"
CONFIDENCE="${CONFIDENCE:-0.95}"
TAGS="${TAGS:-}"
Step 2: Validate Namespace
# Use ontology registry to validate namespace (includes base + user + project ontologies)
PLUGIN_DIR="${CLAUDE_PLUGIN_ROOT:-$(dirname $(dirname $0))}"
if python3 "$PLUGIN_DIR/skills/ontology/lib/ontology_registry.py" --validate "$NAMESPACE" >/dev/null 2>&1; then
echo "Namespace '$NAMESPACE' validated"
else
echo "Error: Invalid namespace '$NAMESPACE'"
echo "Valid namespaces:"
python3 "$PLUGIN_DIR/skills/ontology/lib/ontology_registry.py" --namespaces
exit 1
fi
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 · 329 lines · 6 tokens per session scan A e3409d530ffe
capture is a command published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 6 tokens to every session and 2,979 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
wiring-check
End-of-task wiring gate — verify every change is connected end-to-end across kipi plugins, hooks, MCP tools, agents, bus files, canonical, and rules. Nothing dangling.
issue-closeout
Triage Codex findings via per-finding dispositions, record findingstriaged, close the active issue.
prd-personas
Run the Skeptic persona session against the active draft PRD.
prd-triage
Triage pending findings on the active PRD.
linear-drain
Create the queued Linear projects and issues that shell scripts captured offline.