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 argumentationgit 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/argumentation)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/argumentation"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/argumentation.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.03678 |
| Opus 5 | $0.00043 | $0.01839 |
| Sonnet 5 | $0.00017 | $0.00736 |
| Haiku 4.5 | $0.00009 | $0.00368 |
Grade A, and why
argumentation 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 4d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Construct Arguments
Build rigorous arguments from hypothesis through reasoning to concrete evidence. Every persuasive technical claim follows the same triad: a clear hypothesis states what you believe, an argument explains why it holds, and examples prove that it holds. This skill teaches you to apply that structure to code reviews, design decisions, research writing, and any context where claims need justification.
When to Use
- Writing or reviewing a PR description that proposes a technical change
- Justifying a design decision in an ADR (Architecture Decision Record)
- Constructing feedback in a code review that goes beyond "I don't like this"
- Writing a research argument or technical proposal
- Challenging or defending an approach in a technical discussion
Inputs
- Required: A claim or position that needs justification
- Required: Context (code review, design decision, research, documentation)
- Optional: Audience (peer developers, reviewers, stakeholders, researchers)
- Optional: Counterarguments or alternative positions to address
- Optional: Evidence or data available to support the claim
Procedure
Step 1: Formulate the Hypothesis
State your claim as a clear, falsifiable hypothesis. A hypothesis is not an opinion or a preference -- it is a specific assertion that can be tested against evidence.
- Write the claim in one sentence
- Apply the falsifiability test: can someone prove this wrong with evidence?
- Scope it narrowly: constrain to a specific context, codebase, or domain
- Distinguish from opinions by checking for testable criteria
Falsifiable vs. unfalsifiable:
| Unfalsifiable (opinion) | Falsifiable (hypothesis) |
|---|---|
| "This code is bad" | "This function has O(n^2) complexity where O(n) is achievable" |
| "We should use TypeScript" | "TypeScript's type system will catch the class of null-reference bugs that caused 4 of our last 6 production incidents" |
| "The API design is cleaner" | "Replacing the 5 endpoint variants with a single parameterized endpoint reduces the public API surface by 60%" |
| "This research approach is better" | "Method A achieves higher precision than Method B on dataset X at the 95% confidence level" |
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.
- 4d ago First seen · 258 lines · 86 tokens per session scan A 9f585d1d3a1e
argumentation is a skill published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 3,678 once invoked, about $0.0004 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
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".
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".
review-plan
Independent read-only review of a frozen Engineering plan before execution, in a context that did not cut it: feature or fix snapshot, obligation ledger sweep, phase and validator checks. Returns only PLAN-REVIEW-PASS, PLAN-REVIEW-FAIL, or NEEDS-DESIGN with a snapshot-bound receipt. Never edits a plan artifact.…
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".
review-code
Internal correctness + simplification review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks correctness, error handling, duplication, dead code, and simplification opportunities against the project's own conventions. Findings only; never edits…
review-perf
Internal performance review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks the changed paths for algorithmic and resource regressions: N+1s, hot-path allocations, asset weight, and leaks. Findings only; never edits code.