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.
git clone --depth 1 https://github.com/Habib0x0/spec-driven-pluginWrote 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/habib0x0/spec-driven-plugin/spec-status)<a href="https://agentmods.dev/commands/habib0x0/spec-driven-plugin/spec-status"><img src="https://agentmods.dev/badge/commands/habib0x0/spec-driven-plugin/spec-status/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/habib0x0/spec-driven-plugin/spec-status"><img src="https://agentmods.dev/badge/commands/habib0x0/spec-driven-plugin/spec-status.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 | $0.00010 | $0.01055 |
| Opus 5.5 | $0.00004 | $0.00422 |
| Sonnet 5.5 | $0.00002 | $0.00211 |
| Haiku 4.5 | $0.00001 | $0.00105 |
Grade A, and why
spec-status 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 2mo 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-status Command
Display the current status and progress of a spec.
Workflow
1. Identify Specs
Look for existing specs in .claude/specs/:
If multiple specs exist, show status for all or ask which one to detail.
2. Read Spec Files
For each spec, read:
requirements.md- count user stories AND parse## Depends Onsection for dependency namesdesign.md- verify existstasks.md- count and categorize tasks
Dependency Parsing: Look for a ## Depends On section in requirements.md. Extract each - <spec-name> bullet as a dependency. If the section is absent or contains only comments, the spec has no dependencies.
3. Calculate Progress
Parse tasks.md to count:
- Total tasks
- Pending tasks
- In-progress tasks
- Completed tasks (Status: completed)
- Wired tasks (Wired: yes)
- Verified tasks (Verified: yes)
- Completion percentage (based on verified, not just completed)
Important: A task is only truly "done" when it is completed AND wired AND verified. Display this distinction clearly.
4. Check Todo Sync
Compare tasks.md with Claude Code todos (TaskList):
- Are all tasks synced?
- Are statuses in sync?
- Any orphaned todos?
5. Display Status
Output a formatted status report:
## Spec Status: <feature-name>
### Overview
- Requirements: X user stories
- Design: Complete / In Progress / Missing
- Tasks: Y total
### Progress
| Status | Count | Percentage |
|--------|-------|------------|
| Verified (done) | Z | ZZ% |
| Wired (not verified) | A | AA% |
| Completed (not wired) | B | BB% |
| In Progress | C | CC% |
| Pending | D | DD% |
### Progress Bar
[████████░░░░░░░░] 50% verified
### Integration Health
- Tasks completed but NOT wired: X (these need wiring!)
- Tasks wired but NOT verified: Y (these need testing!)
### Current Focus
- In Progress: T-5: Implement authentication endpoint
### Blocked Tasks
- T-8: Integration tests (blocked by T-5, T-6)
### Dependencies
- auth-system: COMPLETE (10/10 verified) [does not block execution]
- database-migrations: INCOMPLETE (3/5 verified) [BLOCKS EXECUTION]
### Unwired Tasks (Action Needed)
- T-3: Create user profile component (Status: completed, Wired: no)
-> Needs: Route registration, navigation link
### Next Up
- T-6: Create session management
- T-7: Implement logout endpoint
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.
- 2mo ago First seen · 137 lines · 10 tokens per session scan A dd8cacd1fc09
spec-status is a command published in the GitHub repository Habib0x0/spec-driven-plugin (10 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 1,055 once invoked, about $0.0000 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
brief
Brief a PR, MR or the current branch with Punchcard — the reviewer's orientation before the review, never a review.
pr
Review a GitHub PR or GitLab MR with Punchcard and post the review into it.
re-review
Round 2+ review — confirm revisions landed, catch regressions, do not re-litigate.
review-plan
Unbiased review of another session's implementation plan.
review-spec
Unbiased review of another session's spec or design doc.
scaffold-component
Scaffold a single named component from the architecture blueprint with production-depth code.