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 winstonkoh87/Athena-Public --skill decision-journalgit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/winstonkoh87/athena-public/decision-journal)<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/decision-journal"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/decision-journal/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/winstonkoh87/athena-public/decision-journal"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/decision-journal.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 | $0.00035 | $0.01009 |
| Opus 5.5 | $0.00014 | $0.00404 |
| Sonnet 5.5 | $0.00007 | $0.00202 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
decision-journal 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Engine (Journal + Post-Mortem)
Absorbs:
post-mortem-engine
Complete decision lifecycle in one skill: record decisions BEFORE outcomes are known, review them AFTER, classify failures objectively, and track calibration over time.
Triggers
"I've decided to", "logging a decision", "was that a good decision", "calibration", "what went wrong", "post mortem", "failure analysis", "AAR", "I screwed up"
Part 1: Pre-Decision Entry (BEFORE outcome)
## Decision Entry: [YYYY-MM-DD HH:MM]
### The Decision
[What am I deciding to do?]
### The Alternatives
1. [Alternative A and why I rejected it]
2. [Alternative B and why I rejected it]
### My Confidence
[X]% confident this is the right call.
### Key Assumptions (numbered)
1. [Assumption 1]
2. [Assumption 2]
### What Would Change My Mind
[Specific observable evidence that would make me reverse]
### Expected Outcome
- Best case: [description] (probability: X%)
- Most likely: [description] (probability: X%)
- Worst case: [description] (probability: X%)
### Decision Class
- [ ] Reversible (Type 2 — decide fast, adjust later)
- [ ] Irreversible (Type 1 — decide carefully, no undo)
Part 2: Post-Decision Review (30-90 days later)
## Review: [Original Decision Date]
### Actual Outcome
[What actually happened?]
### Assumptions Audit
1. [Assumption 1]: [Correct / Wrong / Partially correct]
2. [Assumption 2]: [Correct / Wrong / Partially correct]
### Calibration
- Stated confidence: X%
- Would I make the same decision with same info? [Yes / No]
- Outcome due to: [good decision / luck / bad decision / bad luck]
Part 3: Post-Mortem (When Things Go Wrong)
Phase 1: Just the Facts (No Interpretation)
Timeline of observable events only. No opinions, no "I should have."
Phase 2: Root Cause (The 5 Whys)
1. Why did [outcome] happen? → Because [cause 1]
2. Why? → Because [cause 2]
3. Why? → Because [cause 3]
4. Why? → Because [cause 4]
5. Why? → Because [ROOT CAUSE]
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 · 135 lines · 35 tokens per session scan A 6d302a334b62
decision-journal is a skill published in the GitHub repository winstonkoh87/Athena-Public (619 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,009 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
Smart Code Review
Review a PR diff: triage its severity, then produce a depth-appropriate review with structured findings, fix suggestions, and a merge decision. Use for code review, review PR, and severity triage requests.
implement-audit
Adversarial review of freshly-built code — find what was missed, what's inconsistent, what breaks. The single code reviewer for the loop. Auto-fired by /implement (phase-4.7); standalone-callable after any substantial change. Writes an implement-audit: line into the report.
spec-audit
Adversarial pre-review of any freshly-written or materially-rewritten SPEC or spec folder, running reviewer consensus (correctness) plus the spirit-check agent (fidelity to the user's verbatim ask — spec.md's Input and Clarifications, or a single-file SPEC's § 0 / § 0a — and to the behavior contract) in one pass and…
review
The vendor review chain the loop skills run and never the model itself — code-review.ts over a git diff, spec-audit.ts over a SPEC or spec folder, policy-review.ts over any artifact — each walking a row of the policy table (policy.json here: Codex first, its declared backup next, never the vendor that wrote the code…
second-opinion
Get an independent review of the current change from a different model family (GPT via Codex, Copilot or Cursor; Gemini via Antigravity) through agent-intern, then check each finding against the code and reconcile it with your own view. Use before merging a risky diff, when stuck on a bug, or when the user asks for a…
gemini-chat-and-reason
Get a second opinion from Gemini via text generation or multi-turn chat. Use for code review, design critique, sanity-checking before commit, or when Claude wants another perspective on a complex decision.