log-outcome

log-outcome is a command for coding agents from robconery/champion. It costs 35 tokens per session (597 once invoked), scanned A, original, MIT.

A command for comparing a past decision or prediction with what actually happened, then recording the result in a decision log.

In plain words
What is it for?
Use it to review a logged decision, check its verdict against reality, and update the record with the result.
Why use it?
It creates a feedback loop so future decisions can learn from real outcomes instead of unverified guesses.

Command

Part of the champion plugin — 15 commands, 21 agents shipped together

Install

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.

agentmods
npx agentmods add commands/robconery/champion/log-outcome
Clone the repo
git clone --depth 1 https://github.com/robconery/champion

Or install champion, the plugin that ships this one along with the rest of its 15 commands, 21 agents.

Wrote 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.

agentmods badge for log-outcome

README.md
[![agentmods](https://agentmods.dev/badge/commands/robconery/champion/log-outcome.svg)](https://agentmods.dev/commands/robconery/champion/log-outcome)
Your own site
<a href="https://agentmods.dev/commands/robconery/champion/log-outcome"><img src="https://agentmods.dev/badge/commands/robconery/champion/log-outcome.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00597
Opus 5 $0.00017 $0.00298
Sonnet 5 $0.00007 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 5d ago against content hash 36e4c19d60d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

log-outcome 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 5d 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.

champion/commands/log-outcome.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin note: this command ships in the champion plugin, so every council agent it names is a plugin agent. When spawning any agent mentioned below, use the champion: prefix for the agent type (e.g. champion:historian, champion:north-star, champion:viewer).

Setup gate: before doing anything else, check that ~/.champion/dossier/PROFILE.md exists. If it does not, stop immediately and tell the user, politely, that the council cannot work without knowing who it fights for: run /champion:setup first (a 20–30 minute interview). Do not proceed in any form until setup is complete.

log-outcome

Grade this past call: $ARGUMENTS

The council only gets smarter if verdicts get checked against reality. This is the feedback loop. Without it, the historian compounds opinions; with it, it compounds truth.

Procedure

  1. Find the entry in the decisions log at ~/.champion/records/decisions-log.md that matches the argument (by subject or date). (If ~/.champion/dossier/context/records.md points the log somewhere else, follow it.) Read its Decision, Verdict, Why, and Dissent.
  2. Establish what actually happened. Ask the user directly for the outcome if it isn't obvious. Did the thing ship? Did it work? Did the predicted upside / risk / objection materialize?
  3. Grade the call honestly:
    • Was the verdict right, wrong, or right-for-the-wrong-reasons?
    • Did the dissent turn out to be correct? (This is the highest-value signal, the minority view we preserved is exactly what we're checking.)
    • What did the council miss, and which voice should have caught it?
  4. Write it back. Append a dated follow-up to that entry in ~/.champion/records/decisions-log.md (edit the file in place, directly under the matching entry):
**Outcome (YYYY-MM-DD):** what actually happened.

**Verdict held?** right / wrong / right-for-wrong-reasons, and whether the dissent was vindicated.

**Lesson for the council:** the one thing the historian should carry forward (e.g. "operator under-weighted maintenance cost again").

Read the full file on GitHub · 37 lines

Changes

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.

  1. 5d ago First seen · 37 lines · 35 tokens per session scan A 36e4c19d60d0

Subscribe to this mod's changes

log-outcome is a command published in the GitHub repository robconery/champion (5 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 597 once invoked, about $0.0002 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 2026-08-31.