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 sushiHex/hardline-mcp --skill playbookgit clone --depth 1 https://github.com/sushiHex/hardline-mcpWrote 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/sushihex/hardline-mcp/playbook)<a href="https://agentmods.dev/skills/sushihex/hardline-mcp/playbook"><img src="https://agentmods.dev/badge/skills/sushihex/hardline-mcp/playbook/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/sushihex/hardline-mcp/playbook"><img src="https://agentmods.dev/badge/skills/sushihex/hardline-mcp/playbook.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 | $0.00109 | $0.02043 |
| Opus 5.5 | $0.00044 | $0.00817 |
| Sonnet 5.5 | $0.00022 | $0.00409 |
| Haiku 4.5 | $0.00011 | $0.00204 |
Grade A, and why
playbook 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
playbook
A play is a fixed shape for passing work between independent hardline jobs and back to you, the orchestrator. Pick the play, choose the lanes, write the brief, run it.
| Play | Shape | Reach for it when |
|---|---|---|
| swim-lanes | N lanes take the same task blind, in parallel; you compare and merge | you want several independent takes, or competing proposals |
| roundtable | blind reviews, then each lane answers the others' critiques and your proposed resolution | the findings conflict and the disagreements need working out |
| ping-pong | lanes take turns, each challenging and adding to the last | an idea needs strengthening by iteration, or the lanes should reach consensus |
Read the play's file before running it. When none fits, run the closest one and say what you changed; the rules below still apply. Plays chain: one play's result, once you have checked it, is the next play's input (e.g. swim-lanes a plan, then ping-pong the merged revision). When the next play works on the artifact itself, first apply the adopted findings to a complete revised draft and pass that, with your rejections and their reasons, not the findings list. Each play keeps its own rules and round limit.
Lanes
A lane is agent + model + effort: one seat in the play. (This is not hardline's mailbox lane, the address your notices arrive at.) Every lane works on the same whole task: in a blind opening round every lane gets the identical brief, and later rounds give each lane the context its play specifies. Lanes differ in agent, model or effort, so their blind spots differ. Lanes given different objectives are split work, not independent takes: nothing they say can agree or conflict.
Default: two lanes, Astra and Fable at high effort. More or other lanes only when asked.
ask_codex_async(prompt, from_agent="claude", label="<play>-<round>-<lane>", model="astra", effort="high", workdir=...)
ask_claude_async(prompt, from_agent="claude", label="<play>-<round>-<lane>", model="fable", effort="high", workdir=..., require_claude=True)
What ships with it
3 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.
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.
- 2d ago Changed · +9 lines 5988e1d8c1fd
- 4d ago First seen · 137 lines · 109 tokens per session scan A 593bd96c1225
playbook is a skill published in the GitHub repository sushiHex/hardline-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 2,043 once invoked, about $0.0004 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 2026-10-31.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
dcc-blender-assembly-pitfalls
Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…
virality-analysis
Use when analyzing why specific content spread or designing a platform-specific test of a sharing hypothesis—define cohorts, metrics, alternatives, confidence, and a stopping rule from observed data. Do not claim causality or access paid/credentialed analytics without the required gates.
color-theory
Use when constructing a reusable palette for a visual system: choose a harmony, assign semantic roles and light/dark token values, account for brand and cultural meaning plus color-vision deficiency, and ensure interaction states never rely on hue alone. Not for measuring an existing interface against an accessibility…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.