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/clarify-featuregit clone --depth 1 https://github.com/mrvladd-d/memobankWrote 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/mrvladd-d/memobank/clarify-feature)<a href="https://agentmods.dev/commands/mrvladd-d/memobank/clarify-feature"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/clarify-feature.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 5.1 | $0.00013 | $0.00912 |
| Opus 5 | $0.00006 | $0.00456 |
| Sonnet 5 | $0.00003 | $0.00182 |
| Haiku 4.5 | $0.00001 | $0.00091 |
Grade A, and why
clarify-feature 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 6d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/clarify-feature - Optional feature ambiguity pass
This command is optional and manual. It does not create tasks, implementation plans, tiers, aliases, or a canonical workflow gate.
0) Input
Expected $ARGUMENTS:
FT-<NNN>for one target feature.
If no feature ID is provided:
- interactive mode: ask the user to provide
FT-<NNN>. - autonomous mode: halt with
HALT_CLARIFICATION_TARGET_REQUIRED.
Do not auto-select a feature.
1) Locate target feature
Find exactly one matching file:
.memory-bank/features/FT-<NNN>-*.md
If no feature file matches, stop and report the missing target.
Feature clarification metadata is optional. If present, valid values are:
clarification_status: pending|complete|blocked
last_clarified: null|YYYY-MM-DD
clarification_questions: 0
Missing clarification metadata is not an error.
2) Read minimal context
Read only the context needed for this feature:
.memory-bank/product.md.memory-bank/requirements.md.memory-bank/features/FT-<NNN>-*.md
Read epics, glossary, invariants, contracts, states, testing docs, runbooks, or other docs only when:
- the feature links to them, or
- they are clearly needed to decide whether ambiguity affects decomposition.
3) Artifact
Create or update only:
.protocols/FT-<NNN>/clarification.md
Do not create:
- task records
- implementation plans
.protocols/FT-<NNN>/decision-log.md.protocols/FT-<NNN>/clarification-report.md- command aliases
- external spec directories
4) Pass-based interview
Each /clarify-feature FT-<NNN> run is one clarification pass.
Rules per pass:
- ask exactly one question at a time
- accept at most 5 answers
- do not reveal queued future questions
- after each accepted answer, update the feature doc
- after each accepted answer, update
.protocols/FT-<NNN>/clarification.md - after each accepted answer, recalculate remaining critical ambiguity
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.
- 6d ago First seen · 128 lines · 13 tokens per session scan A 057f756db6e0
clarify-feature is a command published in the GitHub repository mrvladd-d/memobank (55 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 912 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.