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 agentmods add commands/robconery/champion/log-outcomegit clone --depth 1 https://github.com/robconery/championWrote 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/commands/robconery/champion/log-outcome)<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>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 | $0.00035 | $0.00597 |
| Opus 5 | $0.00017 | $0.00298 |
| Sonnet 5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00060 |
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.
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
championplugin, so every council agent it names is a plugin agent. When spawning any agent mentioned below, use thechampion: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.mdexists. If it does not, stop immediately and tell the user, politely, that the council cannot work without knowing who it fights for: run/champion:setupfirst (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
- Find the entry in the decisions log at
~/.champion/records/decisions-log.mdthat matches the argument (by subject or date). (If~/.champion/dossier/context/records.mdpoints the log somewhere else, follow it.) Read its Decision, Verdict, Why, and Dissent. - 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?
- 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?
- 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").
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.
- 5d ago First seen · 37 lines · 35 tokens per session scan A 36e4c19d60d0
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.