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/mjmorales/claude-prove/remembergit clone --depth 1 https://github.com/mjmorales/claude-proveWrote 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/mjmorales/claude-prove/remember)<a href="https://agentmods.dev/commands/mjmorales/claude-prove/remember"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/remember.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 | $0.00015 | $0.00876 |
| Opus 5 | $0.00008 | $0.00438 |
| Sonnet 5 | $0.00003 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
remember 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remember: $ARGUMENTS
Grow project or user-global CLAUDE.md with a user-authored directive. Never write $ARGUMENTS verbatim — route through optimize (Step 4) and certify (Step 5) before writing. Never write inside the prove-managed block. Never auto-commit.
Step 1: Clarify thin input
If $ARGUMENTS is empty, under ~20 chars, or missing a clear subject/verb/scope, ask one focused free-form question to extract the directive's intent and scope. Do not proceed with a vague draft. Do not delegate thin input to the optimizer.
If $ARGUMENTS is substantive, skip to Step 2.
Step 2: Resolve target
AskUserQuestion (header: "Scope"):
- Project —
<cwd>/CLAUDE.md - User Global —
$HOME/.claude/CLAUDE.md
For User Global, resolve symlinks first:
readlink -f "$HOME/.claude/CLAUDE.md"
Write to the resolved path. Never overwrite the symlink with a regular file — that decouples the active claude-env. If the file does not exist yet and ~/.claude/ resolves into ~/.claude-envs/<env>/, create it at the resolved pool location.
Record the resolved absolute path as TARGET.
Step 3: Choose action
If TARGET does not exist, skip this step — the directive becomes the file's first content (treat as Append, no marker check).
Otherwise, AskUserQuestion (header: "Action"):
- Append — new section at EOF, strictly after
<!-- prove:managed:end -->if present - Update Section — replace an existing named section
On Update Section: ask free-form for the section heading, then read TARGET and locate it. If the heading is ambiguous or absent, fall back to Append and tell the user why.
Step 4: Optimize via llm-prompt-engineer
Invoke the llm-prompt-engineer agent via the Task tool with:
Rewrite the following directive for inclusion in a CLAUDE.md file. CLAUDE.md is consumed as a persistent system directive by Claude on every turn. Apply primacy positioning, operational phrasing (what to do, not how to think), paired constraints (every "never X" gets an "instead, do Y"), and structural anchoring (heading + tight bullets). Preserve all semantic requirements. Output only the rewritten directive markdown — no commentary, no fences.
Directive: $ARGUMENTS
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 · 81 lines · 15 tokens per session scan A 7740527869d5
remember is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 24d ago), licensed MIT. It adds 15 tokens to every session and 876 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.