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/mrvladd-d/memobank/executegit clone --depth 1 https://github.com/mrvladd-d/memobankWhat 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 | $0.00029 | $0.02038 |
| Opus 5 | $0.00015 | $0.01019 |
| Sonnet 5 | $0.00006 | $0.00408 |
| Haiku 4.5 | $0.00003 | $0.00204 |
Grade A, and why
execute 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/execute - Execute One TASK
Status Transition Modes
Status transitions have two modes.
Scheduler mode:
/autopilotand/autonomousown task status transitions.- Scheduler decides closure/failure/blocking eligibility.
/executereturns scoped implementation handoff; it does not close tasks./verifygives functional verdict/evidence; in scheduler mode it does not close/fail/block/promote./red-verifygives semantic verdict for T2/T3; in scheduler mode it does not close/fail/block/promote.- Scheduler must write the closure/failure/blocking decision, final task status, and evidence links to the authoritative indexed
.memory-bank/tasks/TASK-*.task.jsonrecord before/mb-sync. /mb-syncrecords/reconciles already-written task state. It does not decide closure/failure/blocking/promotion and must not sync a decision that exists only in scheduler context.- T0/T1 scheduler closure may use compact evidence / functional PASS according to tier policy.
- T2/T3 scheduler closure requires
VERDICT: PASSplusSEMANTIC_VERDICT: semantic-passbefore scheduler marksdone. - T3 scheduler closure also requires exact markers
HUMAN_CHECKPOINT: doneandROLLBACK_RECOVERY_NOTE: present.
Manual mode:
- Expected T0/T1 simple flow:
/execute -> /verifyfor one TASK. - Manual closure is allowed only when an explicit closure owner exists.
explicit standalone ownermeans either the user directly asked the current top-level agent to close the task, or the top-level agent/orchestrator explicitly runs a manual workflow for one TASK and records that it owns closure. Subagents/worker prompts do not silently become closure owners./verify PASSmay markT0/T1status: doneonly when explicit closure ownership is present and completed evidence has been written to the task recordverifyfield and the compact/full protocol required by tier.- If explicit closure owner is absent,
/verifyrecordsVERDICT: PASS, evidence, and a closure recommendation, leavesstatusunchanged, and tells the scheduler/owner to close. T2/T3manual closure requires/verify PASSplus/red-verifySEMANTIC_VERDICT: semantic-passbeforestatus: doneor/mb-sync; if semantic-pass is absent, leave closure pending or blocked, not done.semantic-concernin manual mode means do not trust the existingdonestate without human review / follow-up.- Do not mix scheduler mode and manual mode inside one task run.
- No persisted
modefield is used.
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 · 182 lines · 0 tokens per session scan A 5f3a02ec3418
execute is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 2,038 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 2026-08-30.
Other commands, from other repositories
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.