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 pjt222/agent-almanac --skill build-consensusgit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/build-consensus)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/build-consensus"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/build-consensus/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/pjt222/agent-almanac/build-consensus"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/build-consensus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 171 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00089 | $0.02578 |
| Opus 5.5 | $0.00036 | $0.01031 |
| Sonnet 5.5 | $0.00018 | $0.00516 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
build-consensus 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 1mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Consensus
Achieve collective agreement across distributed agents without a central authority — using scout advocacy, threshold quorum sensing, and commitment dynamics modeled on honeybee swarm decision-making.
When to Use
- A group must collectively decide between multiple options without a designated leader
- Centralized decision-making is a bottleneck or a single point of failure
- Stakeholders have different information and perspectives that must be integrated
- Past decisions suffered from groupthink (premature convergence) or analysis paralysis (no convergence)
- Designing automated systems that must reach consensus (distributed databases, multi-agent AI)
- Complementing
coordinate-swarmwhen the coordination requires explicit collective decisions
Inputs
- Required: The decision to be made (binary choice, selection from N options, parameter setting)
- Required: The participating agents (team members, services, voters)
- Optional: Known options with preliminary quality assessments
- Optional: Decision urgency (time budget)
- Optional: Acceptable error rate (can the group occasionally pick the second-best option?)
- Optional: Current decision-making failure mode (groupthink, deadlock, flip-flopping)
Procedure
Step 1: Generate Proposals Through Independent Scouting
Ensure the decision space is adequately explored before any advocacy begins.
- Assign scouts to independently explore the option space:
- Each scout evaluates options without knowing other scouts' findings
- Independent evaluation prevents early herding toward popular-but-mediocre options
- Scout count: at minimum, 3 scouts per serious option (for reliability)
- Scouts produce structured assessments:
- Option identifier
- Quality score (normalized 0-100 or categorical: poor/fair/good/excellent)
- Key strengths and risks identified
- Confidence level (how thoroughly was this option evaluated?)
- Aggregate scout reports without filtering — all options above a minimum quality threshold enter the advocacy phase
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.
- 1mo ago First seen · 200 lines · 89 tokens per session scan A 998ba96f8252
build-consensus is a skill published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed 5d ago), licensed MIT. It adds 89 tokens to every session and 2,578 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 2026-09-03.
Other skills, from other repositories
audit-pr
Audit a whole PR against the delivery contract and return MERGE-READY or evidenced blockers with the full URL. Consumes the current review-change REVIEW-PASS receipt instead of re-running review axes; posts a SHA-bound ready comment; never edits or merges. Triggers: "audit-pr", "is this PR ready", "merge gate".
execute-phase
Step executor for units whose triage (unit-lane) decided which steps the unit needs. Implements one triaged step (or all remaining steps), with frozen acceptance, step-local gates, commits, red-gate repair, and diff-size guard. BREAKING: replaced PLAN.md/TASKS.md/progress.md/ACCEPTANCE.md with the unit doc's Tasks…
fold-findings
Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row folded: yes updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".
init-workspace
Adapt the workflow scaffold to a new repository or add only missing substrate blocks to an existing install. Every install, hook, and overwrite needs explicit consent. Triggers: "init-workspace", "set up agentic workflow", "upgrade workflow scaffold".
product-audit
Audit the whole product across code, quality, process, docs, roadmap, and tooling; it owns the repo-wide bug hunt, security research, and broken-version investigation (scoped and budgeted per dimension, as distinct from review-change's change-scoped review). Persist one severity-ranked, F-numbered report with…
review-change
Review a change with only applicable internal axes, classify every finding, persist fix-now work, and return one evidence-backed decision. Findings only; --adversarial N uses isolated reviewers; --synthesize fuses supplied reviewer tables. Triggers: "review-change", "review this change", "adversarial review".