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 skills add gvkhosla/compound-engineering-pi --skill resolve-todo-parallelgit clone --depth 1 https://github.com/gvkhosla/compound-engineering-piWrote 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/skills/gvkhosla/compound-engineering-pi/resolve-todo-parallel)<a href="https://agentmods.dev/skills/gvkhosla/compound-engineering-pi/resolve-todo-parallel"><img src="https://agentmods.dev/badge/skills/gvkhosla/compound-engineering-pi/resolve-todo-parallel.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 5.1 | $0.00026 | $0.00851 |
| Opus 5 | $0.00013 | $0.00426 |
| Sonnet 5 | $0.00005 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
resolve-todo-parallel 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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve all TODO comments using parallel processing, document lessons learned, then clean up completed todos.
Workflow
1. Analyze
Get all unresolved TODOs from .context/compound-engineering/todos/*.md and legacy todos/*.md
Residual actionable work may come from ce:review-beta mode:autonomous after its in-skill safe_auto pass. Treat those todos as normal unresolved work items; the review skill has already decided they should not be auto-fixed inline.
If any todo recommends deleting, removing, or gitignoring files in docs/brainstorms/, docs/plans/, or docs/solutions/, skip it and mark it as wont_fix. These are compound-engineering pipeline artifacts that are intentional and permanent.
2. Plan
Create a task list of all unresolved items grouped by type (e.g., TaskCreate in Claude Code, update_plan in Codex). Analyze dependencies and prioritize items that others depend on. For example, if a rename is needed, it must complete before dependent items. Output a mermaid flow diagram showing execution order — what can run in parallel, and what must run first.
3. Implement (PARALLEL)
Spawn a compound-engineering:workflow:pr-comment-resolver agent for each unresolved item.
If there are 3 items, spawn 3 agents — one per item. Prefer running all agents in parallel; if the platform does not support parallel dispatch, run them sequentially respecting the dependency order from step 2.
Keep parent-context pressure bounded:
- If there are 1-4 unresolved items, direct parallel returns are fine
- If there are 5+ unresolved items, launch in batches of at most 4 agents at a time
- Require each resolver agent to return only a short status summary to the parent: todo handled, files changed, tests run or skipped, and any blocker that still needs follow-up
If the todo set is large enough that even batched short returns are likely to get noisy, use a per-run scratch directory such as .context/compound-engineering/resolve-todo-parallel/<run-id>/:
- Have each resolver write a compact artifact for its todo there
- Return only a completion summary to the parent
- Re-read only the artifacts that are needed to summarize outcomes, document learnings, or decide whether a todo is truly resolved
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.
- 8d ago First seen · 68 lines · 26 tokens per session scan A 431c537a13ca
resolve-todo-parallel is a skill published in the GitHub repository gvkhosla/compound-engineering-pi (51 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 851 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 skills, from other repositories
control-plane-ops
Operar o control-plane local-first do agents-lab com board canônico, long-runs bounded, handoff/checkpoint, rollout/rollback e espelhos externos sem perder governança.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
triage
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
github
Interact with GitHub using the gh CLI. Use for issues, PRs, CI runs, releases, and advanced API queries.
session-triage
Triage das conversas recentes (incluindo branch summaries) para consolidar pendências no board canônico e separar execução imediata vs estabilização.