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 jeffreytse/grimoire-core --skill apply-ackerman-bargaininggit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/apply-ackerman-bargaining)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-ackerman-bargaining"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-ackerman-bargaining/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/jeffreytse/grimoire-core/apply-ackerman-bargaining"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-ackerman-bargaining.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 | $0.00092 | $0.01777 |
| Opus 5 | $0.00046 | $0.00889 |
| Sonnet 5 | $0.00018 | $0.00355 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
apply-ackerman-bargaining 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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Ackerman Bargaining
Set a target price, open with an anchor around 65% of it, and make three further offers at roughly 85%, 95%, and a final non-round number at your actual target — using a calibrated question between each offer and shrinking the increment each time — because the specific anchor placement, decreasing increment sizes, and a precise final number together signal a genuine limit that a simple round-number final offer does not.
Why This Is Best Practice
Why best: A single opening offer followed by ad hoc counters gives the other party no structural signal about how close to your actual limit any given offer is — every counter looks the same, so there's no way for them to distinguish a real final offer from one more round of negotiation. The Ackerman model's specific structure solves this: opening well below target leaves room for several rounds, the strictly decreasing size of each successive increase (a large jump, then a smaller one, then a smaller one still) mimics what a genuinely maxed-out negotiator's offers naturally look like, and a final, deliberately non-round number (an oddly specific figure rather than a round one) reads as the result of actually calculating a true limit rather than as an arbitrarily chosen stopping point.
Chris Voss, "Never Split the Difference" (2016): Voss formalizes the Ackerman model, developed by his colleague Mike Ackerman, as a specific four-offer bargaining sequence: an opening anchor at roughly 65% of the negotiator's target price, followed by three further offers at approximately 85%, 95%, and finally the actual target price — with the final number deliberately not rounded (for instance, ending in a specific, non-round figure) to signal it is the outcome of a genuine calculation rather than an arbitrary stopping point, often paired with a small non-monetary addition at the final offer to reinforce that this is genuinely the end of the room to negotiate. Voss pairs each offer transition with a calibrated question (see apply-tactical-empathy-negotiation) rather than a bare number, so the counterpart experiences each round as a negotiated concession rather than an arbitrary escalation.
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.
- 6d ago First seen · 63 lines · 92 tokens per session scan A a549e0fcdb9a
apply-ackerman-bargaining is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 21d ago), licensed MIT. It adds 92 tokens to every session and 1,777 once invoked, about $0.0005 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
semantic-model-disambiguation
Analyze Power BI semantic models for column-level overlaps that confuse Copilot and Fabric data agents. Detect ambiguity, review with domain expert, apply fixes via MCP.
infrastructure-as-code
Domain: DevOps & Cloud Engineering.
prompt-2-data
Generate comprehensive synthetic relational data for any specified subject with multiple normalized CSV files maintaining referential integrity.
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.
agent-governance
Patterns for adding safety, trust, and policy enforcement to AI agent systems -- control which tools agents can call, what content they process, and maintain accountability through audit trails.