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 agents/managedcode/dotnet-skills/planning-and-todosgit clone --depth 1 https://github.com/managedcode/dotnet-skillsWhat 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 | $0.00021 | $0.02194 |
| Opus 5 | $0.00010 | $0.01097 |
| Sonnet 5 | $0.00004 | $0.00439 |
| Haiku 4.5 | $0.00002 | $0.00219 |
Grade A, and why
planning-and-todos 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 3d 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning and todos
Two context providers support long-running work:
- A todo provider stores trackable work items and gives the agent tools to add, complete, remove, and inspect them.
- An agent mode provider stores the current operating mode and gives the agent tools to read or change it.
Compose these providers directly when you only need planning, or use the Harness Agent to enable both as part of its broader default pipeline.
Todo tools
The .NET and Python providers expose the same model-facing tools:
| Tool | Purpose |
|---|---|
todos_add |
Add one or more items with a title and optional description. |
todos_complete |
Mark one or more items complete and include a completion reason. |
todos_remove |
Remove items that are no longer relevant. |
todos_get_remaining |
Return incomplete items. |
todos_get_all |
Return complete and incomplete items. |
The provider injects the current todo list before each run, so the agent can resume outstanding work.
Plan and execute modes
AgentModeProvider supplies plan and execute modes by default:
- Plan is interactive. The agent analyzes requirements, creates todos, asks clarifying questions, presents a plan, and asks before changing modes.
- Execute is autonomous. The agent works through the plan, makes reasonable choices when details are ambiguous, and marks todos complete.
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.
- 3d ago First seen · 304 lines · 21 tokens per session scan A 1d46a190b7f9
planning-and-todos is an agent published in the GitHub repository managedcode/dotnet-skills (477 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 2,194 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
winui-dev
Builds WinUI 3 desktop applications using Windows App SDK, XAML, and C#. Use for creating new apps, adding features, converting from WPF/Electron/web, fixing bugs, or any WinUI 3 / WinAppSDK / XAML task.
observability
Prometheus-metrikker, OpenTelemetry-tracing, Grafana-dashboards og varsling.
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
forfatter
Norsk teknisk redaktør, tekstforfatter eller innholdsdesigner: klarspråk, AI-markører, anglisismer, fagtermer, mikrotekst.
auth
Azure AD, TokenX, ID-porten, Maskinporten og JWT-validering for Nav-apper.
kafka-agent
Rapids & Rivers, eventdrevet arkitektur, Kafka-mønstre og schema-design.