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/nick-railsback/skill-engine/discardnpx skills add nick-railsback/skill-engine --skill discardgit clone --depth 1 https://github.com/nick-railsback/skill-engineWrote 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/nick-railsback/skill-engine/discard)<a href="https://agentmods.dev/skills/nick-railsback/skill-engine/discard"><img src="https://agentmods.dev/badge/skills/nick-railsback/skill-engine/discard.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 | $0.00036 | $0.00680 |
| Opus 5 | $0.00018 | $0.00340 |
| Sonnet 5 | $0.00007 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade C, and why
discard scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "<install>/<name>-context.proposed/" How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discard
Remove a proposed staging directory. The live contextualizer is not modified. Idempotent — discarding a non-existent proposed dir exits cleanly with a one-line diagnostic.
When to invoke
Invoke /skill-engine:discard <name> when reviewing a proposal that does not warrant promotion — the predictions in Step 1 of REVIEW.md and the disagreement set in Step 2 surface enough divergence that re-running DISCOVER with a --hint=... is the right next move, not promotion. discard is also the path out when the user ticked [x] reject in Step 3: /skill-engine:apply refuses to promote a rejected proposal and points the user here.
Resolving <name> and <install>
Same resolution as /skill-engine:review. See review/SKILL.md § Resolving <name>.
Pre-discard prompt
Before removing anything, render a one-line confirmation naming the path:
Remove <install>/<name>-context.proposed/ (and its .review/ audit trail)? The live <name>-context/ is untouched. [y/N]
Accept y or yes (case-insensitive, leading/trailing whitespace trimmed) as consent. Treat N, blank input, or anything else as decline — the prompt is a single-shot, no re-prompt.
On decline, exit cleanly with:
Discard cancelled. <install>/<name>-context.proposed/ is untouched.
The removal
On consent:
rm -rf "<install>/<name>-context.proposed/"
Exit message:
Removed <install>/<name>-context.proposed/. Live <name>-context/ is untouched.
Idempotent paths
When the proposed dir does not exist at the resolved path (e.g., a stale invocation after an earlier discard, or a slug typo that resolves nowhere), surface:
No proposed staging dir at <install>/<name>-context.proposed/. Nothing to discard.
Exit zero (not an error condition — discarding nothing is a no-op).
When bare invocation finds zero *-context.proposed/ directories under <install>, same shape:
No proposed staging dirs found under <install>. Nothing to discard.
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 · 72 lines · 36 tokens per session scan C 0372f7030252
discard is a skill published in the GitHub repository nick-railsback/skill-engine (2 stars, last pushed 27d ago), licensed MIT. It adds 36 tokens to every session and 680 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
erpaval
Workflow for autonomous software development with the Kiro CLI (open Agent Skills standard). Classifiers route scope, complexity, directory state, and spec readiness before committing to Explore / Research / Plan / Act / Validate, then close the loop with a Compound step that persists lessons to .erpaval/solutions/…
product-discovery
File-first orchestrator for product discovery and spec frameworks. Frames the problem with a Discovery Lead, Product Analyst, or System Architect role. Spawns parallel framework agents (Double Diamond, How Might We, Jobs to Be Done, user stories with INVEST, EARS for AI-coder specs, Gherkin), synthesizes into a PRD or…
agent-ux-patterns
Agent UX patterns and human-in-the-loop design: Twilio A2H protocol, Levels of Autonomy (L0-L5), inbox pattern, progressive trust, decision journal, gate reviews, autonomous work reports. Six-phase methodology from vague pain point to concrete data model via landscape research and multi-direction brainstorming. Use…
meta-prompt-optimizer
Audit and rewrite prompts against Claude Opus 4.7 instruction-following best practices. Produces a scored audit plus a rewritten prompt. Use when the user asks to audit, review, critique, rewrite, improve, optimize, tighten, score, fix, migrate, or draft a prompt — including system prompts, CLAUDE.md files, Claude…
product-strategy
File-first orchestrator for business and product strategy frameworks. Frames the challenge with a CPO / CSO / VP Design role, spawns parallel framework agents (Rumelt kernel + Crux, Wardley Maps, Minto Pyramid as thinking structure, Working Backwards PR-FAQ as discovery artifact), synthesizes outputs into one strategy…
tech-stack-builder
Opinionated tech stack recommendations and settled library references. Two modes: (1) /build-stack runs parallel researcher agents to compare candidates and emit a stack report + ADRs for greenfield projects; (2) direct reference routing for coding with settled defaults. Use when the user asks to recommend a stack…