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/sakrut/ai-code-graph/update-tasks-from-idgit clone --depth 1 https://github.com/sakrut/ai-code-graphWrote 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/sakrut/ai-code-graph/update-tasks-from-id)<a href="https://agentmods.dev/commands/sakrut/ai-code-graph/update-tasks-from-id"><img src="https://agentmods.dev/badge/commands/sakrut/ai-code-graph/update-tasks-from-id.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 | $0.00000 | $0.00558 |
| Opus 5 | $0.00000 | $0.00279 |
| Sonnet 5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
update-tasks-from-id 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.
This is a copy
92% identical to update-tasks-from-id — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Tasks From ID
Arguments: $ARGUMENTS Update multiple tasks starting from a specific ID.
Arguments: $ARGUMENTS
Parse starting task ID and update context.
Bulk Task Updates
Update multiple related tasks based on new requirements or context changes.
Argument Parsing
- "from 5: add security requirements"
- "5 onwards: update API endpoints"
- "starting at 5: change to use new framework"
Execution
task-master update --from=<id> --prompt="<context>"
Update Process
1. Task Selection
Starting from specified ID:
- Include the task itself
- Include all dependent tasks
- Include related subtasks
- Smart boundary detection
2. Context Application
AI analyzes the update context and:
- Identifies what needs changing
- Maintains consistency
- Preserves completed work
- Updates related information
3. Intelligent Updates
- Modify descriptions appropriately
- Update test strategies
- Adjust time estimates
- Revise dependencies if needed
Smart Features
-
Scope Detection
- Find natural task groupings
- Identify related features
- Stop at logical boundaries
- Avoid over-updating
-
Consistency Maintenance
- Keep naming conventions
- Preserve relationships
- Update cross-references
- Maintain task flow
-
Change Preview
Bulk Update Preview ━━━━━━━━━━━━━━━━━━ Starting from: Task #5 Tasks to update: 8 tasks + 12 subtasks Context: "add security requirements" Changes will include: - Add security sections to descriptions - Update test strategies for security - Add security-related subtasks where needed - Adjust time estimates (+20% average) Continue? (y/n)
Example Updates
/taskmaster:update-tasks-from-id 5: change database to PostgreSQL
→ Analyzing impact starting from task #5
→ Found 6 related tasks to update
→ Updates will maintain consistency
→ Preview changes? (y/n)
Applied updates:
✓ Task #5: Updated connection logic references
✓ Task #6: Changed migration approach
✓ Task #7: Updated query syntax notes
✓ Task #8: Revised testing strategy
✓ Task #9: Updated deployment steps
✓ Task #12: Changed backup procedures
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 · 111 lines · 0 tokens per session scan A 7f4d44feb043
update-tasks-from-id is a command published in the GitHub repository sakrut/ai-code-graph (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 558 tokens. A static security scan graded it A with 0 findings. It is 92% identical to update-tasks-from-id, differing in 11 lines, and is treated as a copy.
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.