Borrowing it
Nothing to install: this file belongs to jmeyer1980/neurodivergent-memory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmeyer1980/neurodivergent-memory/main/.github/prompts/memory-driven-issue-execution.prompt.mdgit clone --depth 1 https://github.com/jmeyer1980/neurodivergent-memoryWrote 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/jmeyer1980/neurodivergent-memory/memory-driven-issue-execution)<a href="https://agentmods.dev/commands/jmeyer1980/neurodivergent-memory/memory-driven-issue-execution"><img src="https://agentmods.dev/badge/commands/jmeyer1980/neurodivergent-memory/memory-driven-issue-execution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jmeyer1980/neurodivergent-memory/memory-driven-issue-execution"><img src="https://agentmods.dev/badge/commands/jmeyer1980/neurodivergent-memory/memory-driven-issue-execution.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00032 | $0.00702 |
| Opus 5.5 | $0.00013 | $0.00281 |
| Sonnet 5.5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
Memory-Driven Issue Execution 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 1mo 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
You are working in the currently open repository.
Inputs:
- {{input}}: A GitHub issues URL, issue query, or issue list scope (for example: https://github.com/jmeyer1980/neurodivergent-memory/issues).
Goal: Select one actionable issue and complete it end-to-end using the neurodivergent-memory MCP tools for continuous memory capture.
Workflow (execute in order):
- Discover context:
- Open the provided issues URL/scope.
- Call memory tools to list existing memories.
- Read relevant memories before choosing work.
- Choose issue:
- Pick one issue that is open, implementable, and high-value.
- Prioritize by highest impact first.
- If the highest-impact candidate appears breaking, risky, or architecture-shifting, stop and ask the user for guidance before implementation.
- Briefly justify why this issue was selected.
- Research and plan:
- Inspect the codebase and related files.
- Create a concise implementation plan.
- Store your reasoning, plan, assumptions, and the durable principle behind the work as memories throughout the process.
- Memory cadence is as needed, but frequent enough to maintain clarity and continuity.
- Implement:
- Make the required code changes.
- Keep storing progress notes and decisions to memory while working.
- Do not leave execution-only logs; each substantial implementation memory should explain why the change exists or connect to a reasoning memory that does.
- Run available validation (tests/lint/build) relevant to the change.
- Self-review:
- Review your own diff for correctness, regressions, and style consistency.
- If issues are found, fix them before proceeding.
- Finalize:
- Create a draft pull request first with a concise summary, testing notes, and issue linkage.
- Complete self-review and any follow-up fixes.
- If the result is clean, commit with a clear message and transition the pull request to ready for review.
- Request GitHub Copilot review on the PR.
- Before ending, write a handoff memory that summarizes what was completed, what remains (if anything), and immediate next actions.
- If the work produced a reusable insight, store or update a
logical_analysisorcreative_synthesismemory that states the principle explicitly.
Output format:
- Selected issue: <link + short rationale>
- Plan:
- Changes made: <files + key edits>
- Validation: <commands + results>
- Self-review findings:
- Commit: <hash + message>
- PR:
- Copilot review: <requested/pending/result>
- Memory summary: <what was stored, why, and which durable principle or synthesis was captured>
Rules:
- Use the neurodivergent-memory MCP server continuously for memories (decisions, progress, blockers, outcomes).
- Favor connective synthesis over raw task logging: link implementation memories back to reusable reasoning whenever possible.
- Include a final handoff memory at the end of the run.
- Do not claim completion if tests fail or required checks are not run.
- If blocked by permissions (push/PR/review), report the blocker and provide exact next commands/actions.
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.
- 1mo ago First seen · 68 lines · 32 tokens per session scan A 8af469d56521
Memory-Driven Issue Execution is a command published in the GitHub repository jmeyer1980/neurodivergent-memory (24 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 702 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-12.
Other commands, from other repositories
setup
Install the agmem CLI and index the current repo for project memory.
remember
Save a fact to memini's long-term memory.
handoff
Save, list, or resume a memini session handoff for a fresh session.
pin
Pin a memini memory so it surfaces in every session briefing.
recall
Search memini for what you know about something.
arstart
AgentRecall session opener — status board (no args), project loader ( ), or cold-start bootstrap. Use first every session.