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 nthnclrk/enablement-skills --skill battlecard-buildergit clone --depth 1 https://github.com/nthnclrk/enablement-skillsWrote 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/nthnclrk/enablement-skills/battlecard-builder)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/battlecard-builder"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/battlecard-builder/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/nthnclrk/enablement-skills/battlecard-builder"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/battlecard-builder.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 | $0.00072 | $0.00867 |
| Opus 5.5 | $0.00029 | $0.00347 |
| Sonnet 5.5 | $0.00014 | $0.00173 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
battlecard-builder 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 24d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Battlecard builder
Help a seller decide where the offer fits, what to ask, and which competitive claims the evidence supports.
The job is to say when to compete, when to qualify out, and what to ask before responding.
Fit. "Verified product evidence supports offline plant-floor capture. The supplied implementation assessment does not support a three-week SAP rollout. Ask which requirement is decisive before recommending a fit."
Attack. "Unlike Competitor X, our AI-powered platform delivers unmatched visibility and a modern architecture."
If you cannot name when not to compete, you do not have a card yet.
Inputs
Reuse supplied context first. If a missing company fact would change the result, check the relevant sections of .enablement/context.md when available. Preserve source dates and approval limits.
Ask only for what changes the card:
- The exact competitor, edition, segment, and as-of date
- What the buyer is actually choosing between
- The evidence you have, and what is approved to say
- Who will use the card, and any legal or brand limits
If competitive evidence is missing, identify the claims that cannot be made. A full battlecard needs a research brief first. For an imminent call, provide a safe discovery question and response based only on known facts, with the missing proof clearly marked.
Supporting material
Read references/battlecard-template.md for the fit test, claim types, and optional card shape. Skip it if the user already gave you a structure and only wants lines.
Procedure
- Name the buyer's decision. What they are choosing, why the alternative is credible, which criteria bind. Done when you can say that in two sentences.
- Sort the evidence. Competitor fact, buyer perception, deal pattern, internal hypothesis, approved proof. Date, scope, and permitted use on each. Buyer reports are perception until verified.
- Map fit. Win zones, neutral tradeoffs, loss risks, and qualify-out conditions. A product difference is not an advantage until you can name the mechanism and the buyer outcome.
- Write questions first. Each question should reveal which constraint is binding before the seller responds.
- Write response paths. Acknowledge the goal, diagnose, state the supported difference, cite proof, propose a next step. For stale or unverified comparisons, ask about the buyer's requirement rather than implying a competitor weakness. Absence from a public page is not evidence that a capability is absent.
- Mark landmines. Security, pricing exceptions, confidential data, absolute claims, implementation guarantees.
- Date the card. As-of date, gaps, and what event should trigger a rewrite. Leave unsupplied owners unknown.
What ships with it
2 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.
- 24d ago Changed · +2 lines · -7 tokens per session 0f4e9e4922e4
- 2mo ago First seen · 72 lines · 79 tokens per session scan A 00d0993bb05b
battlecard-builder is a skill published in the GitHub repository nthnclrk/enablement-skills (16 stars, last pushed 25d ago), licensed MIT. It adds 72 tokens to every session and 867 once invoked, about $0.0003 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 2026-08-30.
battlecard-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| battlecard-buildernthnclrk/enablement-skills | Skill | 16 | 25d ago | MIT | A | 72 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |