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/lintgit 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/lint)<a href="https://agentmods.dev/commands/reikor-arg/inmemory/lint"><img src="https://agentmods.dev/badge/commands/reikor-arg/inmemory/lint.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 | $0.00012 | $0.00226 |
| Opus 5 | $0.00006 | $0.00113 |
| Sonnet 5 | $0.00002 | $0.00045 |
| Haiku 4.5 | $0.00001 | $0.00023 |
Grade A, and why
lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run with Bash:
node "${CLAUDE_PLUGIN_ROOT}/hooks/recall.mjs" lint
Reports two things: what your instruction files cost per turn, and phrasing that current models no longer need.
The cost split matters. A CLAUDE.md is in the prompt on every turn forever
— that is the one that compounds. A skill's body is loaded only when invoked;
in the prefix it costs just its description. Do not present a 20,000-token skill
as a 20,000-token-per-turn cost.
On the findings: these are phrasing patterns, not verdicts. Anthropic's
migration notes say prompts written to overcome older models' reluctance now
overtrigger — CRITICAL: YOU MUST use X fires when it should not. But a rule
that genuinely is critical, like never printing a credential, keeps its
emphasis. Read each hit and say which ones you would actually change, and why.
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 · 25 lines · 12 tokens per session scan A d2e64cc5c1b8
lint is a command published in the GitHub repository Reikor-Arg/inmemory (1 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 226 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
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.