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 swan-gtm/gtm-skills --skill call-scorecardsgit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/call-scorecards)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/call-scorecards"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/call-scorecards/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/swan-gtm/gtm-skills/call-scorecards"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/call-scorecards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.00912 |
| Opus 5 | $0.00060 | $0.00456 |
| Sonnet 5 | $0.00024 | $0.00182 |
| Haiku 4.5 | $0.00012 | $0.00091 |
Grade A, and why
call-scorecards 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- call-scorecards — 95% identical, 13 lines differ
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this when nobody can say precisely what a good call looks like. A scorecard turns "what good looks like" into observable, gradeable behaviors per call type, so scoring, coaching, and practice all point at the same standard. The output is a scorecard per key conversation, a scoring cadence, and — when a transcript is supplied — a scored call with evidence per line item.
1. Map the key conversations
List the conversations where deals are won and lost in the user's motion: prospecting/meeting-setting calls, then the closing motion — discovery, demo, pricing and negotiation, close, and champion navigation. Some teams run these in one call; some across months. Each key conversation gets its own scorecard or its own section of one.
2. Build each card — aim small, miss small
Start with the 10–15 most important behaviors on that call type, not a fully baked card. Pull them from what the top reps actually do on real calls, and build with rep and manager input so the card is adopted, not imposed. Group items into the call's natural chunks (opener → body → wrap-up; discovery → pitch → close → navigation) so a low score localizes exactly where a rep is getting stuck. Each item is an observable behavior — "got them to agree they have a problem," not "good discovery." Score each item 1–5. Grow the card only after the scoring habit exists.
Card templates: for meeting-setting calls read references/prospecting-scorecard.md; for the closing motion read references/closing-scorecard.md.
3. Score on a cadence
Volume makes this work: an SDR having 2–3 conversations a day and an AE running 7–8 demos a month can score every one. Reps self-score, managers score a sample, and scores get tracked over time so trends are visible — where the team is improving, which chunk is dragging. Scoring is also proactive deal rescue: a scored miss ("never found out what matters to the decision-maker" = 1) tells the rep exactly what to go back and get before the next call.
4. Practice with the card
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.
- 9d ago First seen · 43 lines · 120 tokens per session scan A 060d236a8f54
call-scorecards is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 120 tokens to every session and 912 once invoked, about $0.0006 per session on Opus 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 2026-09-03.
Other skills, from other repositories
sales-coaching
Sales coaching system — REKS diagnosis (Jacco van der Kooij / Winning by Design), MEDDICC deal reviews (Andy Whyte), JOLT for indecision, call coaching (Jon Barrows, Jason Bay), manager cadence (Kevin Dorsey), and founder-as-coach. Use when building coaching programs, 1:1s, deal reviews, call feedback, or improving…
neuro-linguistic-programming
Applies NLP techniques for rapport-building, reframing, anchoring, and meta-model questioning in business communication. Covers representational system matching, pacing and leading, and linguistic precision tools. Use when preparing for investor pitches, improving sales close rates, navigating board disagreements…
developer-gtm
Build a developer go-to-market motion the way Vercel, Stripe, and Twilio do — open-source/framework flywheel, docs and quickstarts as the funnel, transparent self-serve pricing, PQL signals, DevRel/community as distribution, and a sales motion that enables developer champions instead of cold-pitching them. Use when…
discovery-coach
Discovery call methodology coach. Simulates a buyer while training you on SPIN Selling, Challenger Sale, and Gap Selling techniques in real time.
onboard-new-rep
30-60-90 day ramp plan for new sales hires with milestones, certifications, and warning signs.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".