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 skills/dormstern/forge/ten-percent-deletenpx skills add dormstern/forge --skill ten-percent-deletegit clone --depth 1 https://github.com/dormstern/forgeWrote 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/dormstern/forge/ten-percent-delete)<a href="https://agentmods.dev/skills/dormstern/forge/ten-percent-delete"><img src="https://agentmods.dev/badge/skills/dormstern/forge/ten-percent-delete.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 | $0.00084 | $0.01039 |
| Opus 5 | $0.00042 | $0.00519 |
| Sonnet 5 | $0.00017 | $0.00208 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
ten-percent-delete 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The 10% Delete Rule
Every SHAPE proposes killing at least 10% of the release scope. Not optional. Not "if convenient." Not "if I can find anything."
Why
Products accumulate features the way attics accumulate boxes. The longer you ship, the more drag your product carries — features nobody uses but everyone has to maintain, code paths nobody owns, edge cases that exist for one user from 2024.
The rule forces every release to interrogate product shape. If you can't find 10% to kill, you're not looking hard enough or you've never been honest with the data.
What qualifies for the kill list
In order of how easy they are to spot:
- Features with
post_mvp_status: "evaluate"and no growth in usage signals across 2 releases. They've earned a verdict. - Features with no
requested_byowner. Anonymous features are deletion candidates by default. - Tech debt that's never going to be paid because the feature it underpins isn't valuable. Kill the feature; the debt vanishes.
- Edge-case branches in code paths that haven't fired in production for 90 days. If your audit log has 0 events for that path, it's dead code, not a feature.
- Settings/toggles nobody changes. A toggle nobody flips is a hidden cost — cognitive load on every PR review.
- Features that contradict NEVER. They shouldn't exist. Use the kill list to remove them.
- Features that lost the bake-off. If you A/B tested and lost, kill the loser. Don't keep both.
What doesn't qualify
- Features users like that you don't like.
- Features that might be useful "someday."
- Features blocked on external dependencies (those go in
progress.mdOpen Questions, not kill list). - Features that are technically working but feel ugly. (Ugly ≠ deletable.)
How /forge:shape enforces it
When /forge:shape runs, the orchestrator:
- Scans
features.jsonforpost_mvp_status: "evaluate"items, low-signal items, no-owner items, contract-violation items. - Cross-references against
releases.jsonsignals (low engagement / negative signals → stronger kill candidate). - Renders the kill list in the SHAPE hero card with reasons (≤6 words each).
- Computes the kill ratio (kill list / total in-flight scope).
- If <10%, refuses to proceed until the user either expands the list or explicitly states "no candidates qualify and here's the evidence."
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.
- 5d ago First seen · 78 lines · 84 tokens per session scan A 7a58543e437a
ten-percent-delete is a skill published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 1,039 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…