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/reikor-arg/inmemory/digestgit clone --depth 1 https://github.com/Reikor-Arg/inmemoryWrote 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/commands/reikor-arg/inmemory/digest)<a href="https://agentmods.dev/commands/reikor-arg/inmemory/digest"><img src="https://agentmods.dev/badge/commands/reikor-arg/inmemory/digest.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 | $0.00009 | $0.00145 |
| Opus 5 | $0.00005 | $0.00072 |
| Sonnet 5 | $0.00002 | $0.00029 |
| Haiku 4.5 | $0.00001 | $0.00015 |
Grade A, and why
digest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run with Bash:
node "${CLAUDE_PLUGIN_ROOT}/hooks/recall.mjs" digest $ARGUMENTS
Without a week, it uses the most recent one. Output is raw material, not prose: the verbatim first line of each turn, the files touched ranked by how many sessions touched them, and the commands run.
Write the narrative yourself from that material. Quote the user's own words when describing what was asked. Do not assert outcomes the material does not show — it records what was asked and touched, not whether it worked.
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.
- 3d ago First seen · 19 lines · 0 tokens per session scan A d24a7506e2c8
digest is a command published in the GitHub repository Reikor-Arg/inmemory (1 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 145 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 2026-08-31.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
health
Run the Self-Star Doctor - a green/yellow/red health board across all 7 junctions of the self- loop.
plan-new
Plan a complex project with discovery, structure, and kill criteria.
search-code
Hybrid code search — semantic + keyword + BM25.
context-stats
Show context window usage, active tier, and system stats.
evolution
Show what the system learned and changed recently.