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 SethGammon/Citadel --skill improvegit clone --depth 1 https://github.com/SethGammon/CitadelWrote 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/sethgammon/citadel/improve)<a href="https://agentmods.dev/skills/sethgammon/citadel/improve"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/improve/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/sethgammon/citadel/improve"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 193 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00048 | $0.04228 |
| Opus 5.5 | $0.00019 | $0.01691 |
| Sonnet 5.5 | $0.00010 | $0.00846 |
| Haiku 4.5 | $0.00005 | $0.00423 |
Grade A, and why
improve 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/improve — Autonomous Quality Engine
Orientation
Use when: Scoring a target against a rubric and iteratively improving it. Rubric required at .planning/rubrics/{target}.md (Phase 0 creates one if missing).
Don't use when: Refactoring without a rubric (use /refactor), one-time code review (use /review), or debugging a specific bug (use /systematic-debugging).
Invocation
/improve {target} # Loop until plateau or all axes >= 8.0
/improve {target} --n=3 # Run exactly N loops then stop
/improve {target} --axis={name} # Force-attack a specific axis (skips scoring)
/improve {target} --score-only # Score and report, no attack
/improve {target} --continue # Resume from campaign state (used by daemon)
/improve citadel # Targets Citadel itself
target is a slug that maps to .planning/rubrics/{target}.md.
If no rubric exists, run Phase 0 first.
Campaign Mode
When invoked with --n or --continue, improve operates in campaign mode and maintains a campaign file that daemon can attach to.
Campaign file: .planning/campaigns/improve-{target}.md, created automatically on the first invocation with --n (full template: docs/QUALITY_LOOPS.md#campaign-file-template).
Frontmatter: version, id (improve-{target}-{ISO-date-slug}), status: active, type: improve, target, total_loops ({n} or unlimited), completed_loops: 0, current_level (from rubric frontmatter), estimated_cost_per_loop: 12, started.
Body: status and direction lines, a Loop History table (Loop | Axis Attacked | Outcome | Score Movement), and a Continuation State block (next_loop, last_scorecard_log, last_outcome, phase_within_loop, level_up_triggered).
Campaign lifecycle
Update phase_within_loop at each phase: scoring → selected-{axis} → attacking-{axis} → verifying → not-started.
On loop complete: increment completed_loops, update next_loop/last_scorecard_log/last_outcome, append Loop History row.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 295 lines · 48 tokens per session scan A ae411ed3352d
improve is a skill published in the GitHub repository SethGammon/Citadel (924 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 4,228 once invoked, about $0.0002 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
gerrit-task-query
Use when asked to check, list, or act on tasks for a Gerrit change. Triggers on phrases like "what tasks are blocking", "which tasks are actionable", "check task status", "what do I need to do for this change", "what is blocking this change".
gerrit-workflow
This skill should be used when the user asks to "submit a change to Gerrit", "push for review", "upload a patch", "update a change in Gerrit", "add a patch set", "work with Gerrit", "push to refs/for", "fix a missing Change-Id", "amend a Gerrit change", or any task involving git operations in a repository hosted on…
doubt-driven
Use when a non-trivial decision sits under uncertainty and correctness matters more than speed. Not for patch review: use review. Not for plan attacks: use load-bearing-assumption-test.
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
pr-review
Team baseline for PR and code review — produces scope, blockers, nits, and strengths. Auto-triggers when you say review this PR, check this diff, review these changes, pre-review before I share, what do you think of this PR, or review the diff on this branch. Defers to any other installed skill whose description…