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/keithwhatling/topo/topo-updategit clone --depth 1 https://github.com/KeithWhatling/ToPOWrote 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/keithwhatling/topo/topo-update)<a href="https://agentmods.dev/commands/keithwhatling/topo/topo-update"><img src="https://agentmods.dev/badge/commands/keithwhatling/topo/topo-update.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 | $0.00042 | $0.00925 |
| Opus 5 | $0.00021 | $0.00463 |
| Sonnet 5 | $0.00008 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
topo-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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/topo-update $ARGUMENTS
Parse arguments as: Action ComponentType ComponentName
- Action:
add|modify|remove - ComponentType:
DE|SL|CL|API|SF|BP|UC|CFG|IB - ComponentName: the identifier or display name
Examples:
/topo-update add DE contoso_projecttask/topo-update add SL ValidateProjectBudget/topo-update modify CL OnFormLoad/topo-update remove BP Order - On Create - Notify ERP/topo-update add IB PaymentGateway
Step 1: Load the Map
Read docs/solution-map.topo. If missing, instruct user to run /init-project.
Step 2: Route by Action
ADD
-
Check if a block with this type and name already exists. If yes, ask: did you mean
modify? -
Determine the correct SOP from
docs/topo-standard-operating-procedures.md:- DE > SOP-2
- SL > SOP-3
- CL > SOP-4
- API > SOP-5
- SF > SOP-6
- BP > SOP-7
- UC > SOP-8
- CFG > SOP-9
- IB > SOP-10
-
Follow the SOP step-by-step. Prompt the user for required attributes. Pre-fill what you can infer from context (e.g. if you just created a plugin, you know the entity, message, and stage).
-
Create the block in the correct section (section order per language spec).
-
Automatic cross-updates:
- For every
depends_onentry: find target block, add this component to itsdepended_on_by - For
[SL],[CL],[UC]: update parent[DE]block's server-logic/client-logic/ui-controls list - For
[CL]: verify parity is set; if not, prompt for it - For
[API]: update backing[SL]block'sdepended_on_by
- For every
-
Confirm all changes made (list every block touched).
MODIFY
-
Find the existing block. If not found, ask: did you mean
add? -
Show the current block to the user.
-
Ask what needs to change. Apply changes.
-
Dependency reconciliation:
- Compare old depends_on with new depends_on
- Removed dependencies: remove this component from old target's depended_on_by
- Added dependencies: add this component to new target's depended_on_by
- Same for depended_on_by changes
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.
- 4d ago First seen · 111 lines · 42 tokens per session scan A 746290b03290
topo-update is a command published in the GitHub repository KeithWhatling/ToPO (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 925 once invoked, about $0.0002 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.
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.