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/applygit clone --depth 1 https://github.com/robconery/championWhat 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 | $0.00058 | $0.02305 |
| Opus 5 | $0.00029 | $0.01153 |
| Sonnet 5 | $0.00012 | $0.00461 |
| Haiku 4.5 | $0.00006 | $0.00231 |
Grade A, and why
apply 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 2d 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 — 100 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.
apply, should the user go for this job?
The listing:
$ARGUMENTS
This is the decision engine pointed at a job. The output is one of two things and nothing in between: a tailored application package (resume + cover letter, drafted in markdown and run through the writing gauntlet, then rendered to PDF only after the user approves the words), or a PASS with the real reason. We do not write a resume for a job the user shouldn't take, and we never hand them a finished PDF they haven't approved in markdown first.
Two truths must stay separate the whole way through:
- Is the job any good? (money, role, company, trajectory)
- Should the user do this, and can they?: and this one matters more.
A job can be a high-stakes deviation for this user specifically: their stance on working for others, any active contract they've committed to protect, and any wound a past employer left are all in ~/.champion/dossier/PROFILE.md and ~/.champion/dossier/CAREER.md. Taking a job is not neutral, it's potentially the sabotage pattern firing, potentially a brave move, or potentially a contract breach. The gauntlet's job is to tell which.
0, Get the real listing
If $ARGUMENTS is a URL, fetch it (WebFetch). If it's pasted text, use it. Extract and pin down before debating: company, role/title, seniority, comp/equity if stated, location/remote, key requirements, who they want. If comp isn't stated, the researcher estimates the band.
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.
- 2d ago First seen · 100 lines · 58 tokens per session scan A f13e2dc9d0b5
apply is a command published in the GitHub repository robconery/champion (5 stars, last pushed 29d ago), licensed MIT. It adds 58 tokens to every session and 2,305 once invoked, about $0.0003 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.