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 Firstp1ck/pi-coding-agent-forge --skill stop-slopgit clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-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/firstp1ck/pi-coding-agent-forge/stop-slop)<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/stop-slop"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/stop-slop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/firstp1ck/pi-coding-agent-forge/stop-slop"><img src="https://agentmods.dev/badge/skills/firstp1ck/pi-coding-agent-forge/stop-slop.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.01382 |
| Opus 5.5 | $0.00022 | $0.00553 |
| Sonnet 5.5 | $0.00011 | $0.00276 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
stop-slop 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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stop Slop
Measure specific style patterns, revise the passages that need work, and check the result again.
When to use
- After Unslop has edited a draft, to get repeatable feedback rather than another subjective rating.
- On an existing draft, even when Unslop is unavailable or was not used.
- When you need to compare a revision with its original text and identify regressions.
Do not load this skill for exact-response requests or treat source code as prose.
Inputs and assumptions
Get the text or file, intended audience, tone, and protected material. Preserve facts, quotations, commands, identifiers, numbers, citations, and required legal or safety wording. Ask about unclear scope before editing.
The evaluator handles English plain text and common Markdown. It uses fixed phrase rules and grammar heuristics, not a language model. All scores are penalties from 0 to 100, where lower means fewer measured patterns. They do not measure authorship, truth, authenticity, or whether the reader will like the text.
Resolve bundled paths below against this skill directory, not the working directory. Use an absolute, quoted script path when running from the user's project. Never interpolate the draft into shell code. Pass a file or pipe UTF-8 bytes through stdin.
Portable workflow
-
Locate the draft. If Unslop just edited it, use that result as this check's baseline. Unslop is optional; do not install or invoke it as a prerequisite.
-
Keep an exact baseline copy in a task-local or private temporary location before making further edits. Do not overwrite an existing file or put user drafts inside this package.
-
Run the evaluator on that baseline, using the resolved path to
scripts/slopcheck.mjs:node "<skill-directory>/scripts/slopcheck.mjs" "<baseline-file>" --json -
Read the scores, warnings, strongest issues, and findings. Grammar candidates need judgment. A matched phrase is not proof that the sentence is bad. A zero score is not proof that it is good. If no prose was found, fix the input selection rather than claiming success.
-
If the user authorized edits, revise the passages that hurt clarity or violate the requested style. State existing facts more directly. Do not invent evidence, delete qualifications, change a quotation, or pad the text to lower a density score. If the request is evaluation-only, report the findings without editing.
-
Run the same evaluator on the revision and compare it with the original text:
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/evaluation.md 2.8 KB
- references/upstream/examples.md 1.6 KB
- references/upstream/LICENSE 1.0 KB
- references/upstream/phrases.md 2.8 KB
- references/upstream/PROVENANCE.json 897 B
- references/upstream/SKILL.md.txt 2.6 KB
- references/upstream/structures.md 5.1 KB
- scripts/analyzer.mjs 11 KB runs code
- scripts/rules.mjs 7.3 KB runs code
- scripts/slopcheck.mjs 9.3 KB runs code
- scripts/text.mjs 8.4 KB runs code
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.
- 1mo ago First seen · 77 lines · 56 tokens per session scan A 4131520d74dd
stop-slop is a skill published in the GitHub repository Firstp1ck/pi-coding-agent-forge (90 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 1,382 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
convex-component-authoring
How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management.
npm-docs
Use this skill whenever the user asks about npm, package management, publishing packages, semantic versioning, npm CLI commands, or Node.js dependencies. Covers npm 12.x including the registry, scopes, organizations, security (audit, provenance, 2FA), CI/CD integration, workspaces, scripts, .npmrc configuration, and…
convex-component-authoring
How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management.
dependency-manager
Manage project dependencies — update packages, audit vulnerabilities, resolve conflicts, and keep dependencies healthy. Use when updating packages, fixing vulnerability alerts, or resolving dependency issues.
colab-finetuning
Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…