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/sequenzia/claude-plugins/updategit clone --depth 1 https://github.com/sequenzia/claude-pluginsWhat 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 | $0.00009 | $0.00519 |
| Opus 5 | $0.00005 | $0.00260 |
| Sonnet 5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
update 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 yesterday.
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
Re-analyze the specification document and update the existing task list with changes.
Input document: @$1
Process
-
Locate existing task list
- If project name provided ($2): Read
tasks/$2.tasks.json - Otherwise: Derive project name from spec filename
- If project name provided ($2): Read
-
Read current task list
- Load existing tasks with their current statuses
- Note which tasks are complete, in_progress, or blocked
-
Re-analyze the specification
- Parse the updated specification document
- Extract all current requirements
-
Compare and reconcile
For each requirement in the updated spec:
- Unchanged: Keep existing task, preserve status
- Modified: Update task description/criteria, preserve status if in_progress
- New: Create new task with stable ID
For existing tasks not in updated spec:
- Mark as "obsolete" (don't delete - preserve history)
-
Recalculate dependencies
- Update dependency graph for any structural changes
- Recalculate blocked_by for all non-complete tasks
- Rebuild execution phases
-
Update metadata
- Increment version (minor bump for structural changes)
- Update last_updated timestamp
- Recalculate total_tasks and completion_percentage
-
Write updated task file
- Backup previous version (rename to .tasks.json.bak)
- Write new task list
-
Display change summary
Format output as:
## Task List Updated: <project-name>
**Version:** <old> -> <new>
### Changes Summary
- **New tasks:** X
- **Modified tasks:** Y
- **Obsolete tasks:** Z
- **Unchanged tasks:** W
### New Tasks Added
- TASK-XXX: <title> (priority, complexity)
- TASK-YYY: <title> (priority, complexity)
### Tasks Marked Obsolete
- TASK-ZZZ: <title> (was: status)
### Modified Tasks
- TASK-AAA: <change description>
### Progress Impact
- Completion: X% -> Y%
- Total tasks: A -> B
### Next Actions
Run `/spec-task-manager:next` to see recommended tasks.
If this is a significant restructuring, warn about potential workflow disruption.
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.
- yesterday First seen · 83 lines · 9 tokens per session scan A 2293b5373c09
update is a command published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 519 once invoked, about $0.0000 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 2026-08-31.
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.