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 andr-ca/agentharness --skill big-work-plan-reviewgit clone --depth 1 https://github.com/andr-ca/agentharnessWrote 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/andr-ca/agentharness/big-work-plan-review)<a href="https://agentmods.dev/skills/andr-ca/agentharness/big-work-plan-review"><img src="https://agentmods.dev/badge/skills/andr-ca/agentharness/big-work-plan-review.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 | $0.00080 | $0.01555 |
| Opus 5 | $0.00040 | $0.00777 |
| Sonnet 5 | $0.00016 | $0.00311 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
big-work-plan-review 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 7d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Big-Work Adversarial Plan Review
Ported from a workflow validated on a real design (an ntfy ingestion + persona memory pipeline) that went from roughly 3.5/10 to roughly 8.5/10 across 4 review rounds — each round finding genuine production-breaking defects a single author missed: processed-before-persisted data loss, an LLM call blocking a shared stream thread, mutable-JSONL status corruption, an answer-handling path that let contradiction answers poison an importance-rule store, and free-text LLM writes into what should have been a structured graph.
This is a from-description port. It was written from a GitHub issue
proposal, not from the original Cursor-format draft it references
(~/.cursor/skills/big-work-plan-review/SKILL.md, on the proposing
operator's own machine) — that draft was unreachable from the session
that built this file. Reconcile against the original draft if it
surfaces later; treat this version as functionally complete in the
meantime, not as a placeholder.
When to use this
Big, stateful, or concurrent work: new systems, pipelines, daemons, anything with multiple writers, ordering dependencies, or state that outlives a single request. The cost of a design mistake here is a production incident, not a failed test.
When NOT to use this: a scoped bug fix with one clear resolution, a
single-file change, or anything requirements-clarification already
covers by itself. Running a two-reviewer adversarial loop on a small
change is pure overhead — match the ceremony to the blast radius.
The loop
-
Research verified facts, not assumptions. Probe the live systems this design touches — actual schemas, actual message shapes, actual failure behavior — before writing a line of the plan. Record findings in a "Current state (verified)" section so a reviewer can tell what you checked from what you assumed.
-
Write the plan. One doc in
docs/plans/, with these sections at minimum:- Goal
- Current state (verified)
- Architecture
- Exact schemas / DDL / message contracts
- Module contracts (inputs, outputs, invariants each module owns)
- Failure-modes table (what breaks, how it's detected, what happens next)
- Testing approach
- Out of scope
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.
- 7d ago First seen · 141 lines · 80 tokens per session scan A e36b375e0803
big-work-plan-review is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,555 once invoked, about $0.0004 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 skills, from other repositories
projectatlas
Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.
codex-coding-plugin
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.
execute-spec-in-fork
Orchestrate one approved SPEC READY through a same-directory Codex App fork: create and name the execution task, ask it to run spec-executor, route decisions through Codex Task Messenger, validate the returned receipt, and archive a completed child. Use only when the user explicitly asks to execute an approved spec in…
nopus-simplify
Rewrite the immediately preceding assistant response with clearer and more direct prose when the user invokes this skill.
breaking-down-the-work
Splits scope into a product-first work breakdown that follows the 100% rule, keeps pieces from overlapping, uses outline numbers, and gives every piece a dictionary entry. Use when an epic, feature, or new subsystem needs a clean split into deliverables, or one source of truth before folders or work begin. Do not use…
closing-stale-packets
Brings an abandoned or half-filled change packet to an honest terminal state by completing it, closing it with a recorded rationale, or deleting it. Use when ng status flags a scaffold or invalid packet, a long session left a draft behind, or work was abandoned mid-packet. Do not use for an actively in-progress…