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 Doris-Labs/sales-skills --skill competitive-battlecardgit clone --depth 1 https://github.com/Doris-Labs/sales-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/doris-labs/sales-skills/competitive-battlecard)<a href="https://agentmods.dev/skills/doris-labs/sales-skills/competitive-battlecard"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/competitive-battlecard/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/doris-labs/sales-skills/competitive-battlecard"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/competitive-battlecard.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 | $0.00076 | $0.01352 |
| Opus 5.5 | $0.00030 | $0.00541 |
| Sonnet 5.5 | $0.00015 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
competitive-battlecard 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 2mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitive Battlecard
Purpose
Turn a competitive threat into a deal-specific plan: an honest read of where you genuinely win and where they genuinely win, landmines to set early, trap questions that expose their weakness, rebuttals to their likely claims, and the proof points that back each one. The goal is to shape the buyer's evaluation criteria before the competitor does — not to spin.
Inputs
- The competitor's name (and edition/tier if known)
- How the competitor surfaced (buyer mentioned, incumbent, RFP shortlist)
- The deal context: stage, who's evaluating, their stated criteria and pains
- Your real differentiators and your real gaps (be honest with yourself first)
Method
- Establish the honest baseline. Split the field into where we win and where they win. If you can't name a category where they legitimately beat you, you don't understand the competitor — and the buyer will smell the spin. Tie each side to this buyer's stated criteria, not a generic feature grid.
- Plant landmines early. A landmine is a criterion you seed into the buyer's evaluation that the competitor structurally fails. Plant it as a question the buyer should "make sure to ask any vendor," not as an attack. Set it while you still control the agenda — before the competitor's demo, not after.
- Build trap questions. A trap question is one the buyer asks the competitor that exposes a known weakness, where any honest answer hurts them. Frame it neutrally so it lands as due diligence, not a hit job.
- Prepare rebuttals to their likely claims. For each thing the competitor will say about you, write the reframe — acknowledge the grain of truth, then pivot to the dimension where you win. Never flatly deny a true claim; you lose credibility.
- Attach proof points. Every counter needs evidence: a customer story, a metric, a reference, a doc. A battlecard without proof is just opinion.
Battlecard output format:
Competitor: <name> (<edition/tier>)
Deal: <account> — <stage> — surfaced via <how>
THEIR STRENGTHS (honest)
- <real strength> → why it matters to THIS buyer
THEIR WEAKNESSES
- <real gap> → tied to <buyer criterion it threatens>
OUR COUNTERS
- <their weakness> → <our reframe / where we win> → proof: <evidence>
LANDMINES TO PLANT (early, before their demo)
- "Make sure to ask any vendor: <criterion they fail>"
TRAP QUESTIONS (for the buyer to ask them)
- "<neutral question>" → exposes <weakness>; any honest answer hurts them
REBUTTALS (when they attack us)
- They'll say: "<their claim>" → You say: "<acknowledge truth> + <pivot to win>"
PROOF POINTS
- <story / metric / reference / doc> → supports <which counter>
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.
- 2mo ago First seen · 113 lines · 76 tokens per session scan A 944fc96bdd81
competitive-battlecard is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 1,352 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 2026-08-31.
competitive-battlecard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| competitive-battlecardDoris-Labs/sales-skills | Skill | 3 | 5mo ago | MIT | A | 76 | Claude Code |
| lynquGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 40 | Claude Code, Codex |
| lynqu-sales-followupGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 39 | Claude Code, Codex |
| lynqu-deal-deskGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 48 | Claude Code, Codex |
| lynqu-event-blitzGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 47 | Claude Code, Codex |
| lynqu-lead-managementGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 40 | Claude Code, Codex |
| lynqu-outreachGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 41 | Claude Code, Codex |