Borrowing it
Nothing to install: this file belongs to rshade/finfocus. 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/rshade/finfocus/main/.claude/commands/speckit.revisit.mdgit clone --depth 1 https://github.com/rshade/finfocusWrote 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/rshade/finfocus/speckit.revisit)<a href="https://agentmods.dev/commands/rshade/finfocus/speckit.revisit"><img src="https://agentmods.dev/badge/commands/rshade/finfocus/speckit.revisit/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/rshade/finfocus/speckit.revisit"><img src="https://agentmods.dev/badge/commands/rshade/finfocus/speckit.revisit.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 | $0.00023 | $0.01236 |
| Opus 5.5 | $0.00009 | $0.00494 |
| Sonnet 5.5 | $0.00005 | $0.00247 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
speckit.revisit 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Purpose
During implementation (/speckit.implement), issues may arise that cannot be resolved at the task level:
- Constitution violations discovered in generated code or tests
- Conflicting instructions from different sources (e.g., mode prompts vs constitution)
- Design gaps where the plan doesn't address a discovered requirement
- Technical blockers where the chosen approach doesn't work
- Scope creep where implementation reveals missing requirements
This command creates a formal escalation path to revisit earlier phases without losing implementation progress.
Outline
-
Setup: Run
.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasksfrom repo root and parse FEATURE_DIR. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot"). -
Capture the Issue: Document the discovered problem:
- Issue Type: Select from [constitution-violation | instruction-conflict | design-gap | technical-blocker | scope-creep]
- Description: Clear statement of what was discovered
- Discovery Context: Where/when the issue was found (task ID, file, line)
- Impact: What cannot proceed until this is resolved
-
Classify Escalation Level: Determine which phase needs revisiting:
Issue Type Escalation Target Action constitution-violation Plan + Tasks Update plan to comply, regenerate affected tasks instruction-conflict Research + Plan Research the conflict, update plan with resolution design-gap Spec + Plan Clarify spec, update plan with missing design technical-blocker Research Research alternatives, update research.md scope-creep Spec Re-run /speckit.clarify to capture new requirements -
Create Issue Log: Append to
FEATURE_DIR/issues.md:
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 · 139 lines · 23 tokens per session scan A 8831a5f303c4
speckit.revisit is a command published in the GitHub repository rshade/finfocus (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,236 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 2026-08-31.
Other commands, from other repositories
scan
Scan AWS account for cost optimization.
oma-platform-review
A command that reviews an existing AI-agent platform deployment for GPU capacity, monitoring coverage, gateway safety checks, unusual costs, and security weaknesses. It saves a diagnostic report and suggested improvements to a state file.
langgraph-checkpoints
LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, or debugging with state history. Triggers on LangGraph checkpoint, persistence, fault tolerance, resume workflow, state history, checkpointer, thread state.
langgraph-human-in-loop
LangGraph human-in-the-loop patterns. Use when implementing approval workflows, manual review gates, user feedback integration, or interactive agent steps. Triggers on human-in-loop, approval workflow, review gate, interrupt, user feedback, manual approval, interactive agent.
archive-ledger
../../../shared/commands/archive-ledger.md.
deploy
Builds and deploys your project to a cloud provider of your choice.