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 skills/gaasher/agent-loop-skills/blue-teamnpx skills add gaasher/Agent-Loop-Skills --skill blue-teamgit clone --depth 1 https://github.com/gaasher/Agent-Loop-SkillsWrote 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/gaasher/agent-loop-skills/blue-team)<a href="https://agentmods.dev/skills/gaasher/agent-loop-skills/blue-team"><img src="https://agentmods.dev/badge/skills/gaasher/agent-loop-skills/blue-team.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 5.1 | $0.00201 | $0.03658 |
| Opus 5 | $0.00101 | $0.01829 |
| Sonnet 5 | $0.00040 | $0.00732 |
| Haiku 4.5 | $0.00020 | $0.00366 |
Grade A, and why
blue-team 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 6d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blue Team
A defensive fixer loop — the inverse of red-team. The artifact is the target, now writable;
the feedback signal is two-part, like optimize-loop: a gate that must hold (nothing that passed
before regresses) and a metric that must drop (the count of open failure classes, toward zero). You
point it at a set of concrete failed cases and fix them one root-cause class at a time. Each
iteration you patch one class, then run tools/verify.py, and keep the patch only if it closes the class
with no regression, else revert. You loop until every class is closed (dry) or the budget runs out,
then hand the patch set off as a pull request. This is the fix half of a find→fix setup (see
Pairing).
The failed cases come from a real source; tools/ingest.py normalizes any of them into one catalogue:
oraclemode — ared-teamfailures.jsonl: each case is an input where the target's verdict disagrees with a ground-truth oracle. A case is closed when target and oracle now agree; a regression is a benign<holdout>input that newly disagrees (most often a new over-block).testsmode — a CI/CD test-failure report (pytest --junitxml/ JUnit XML, or a list of failing node ids): each case is a failing test. A case is closed when its test now passes; a regression is any other test that was passing and now fails.
When to use
Use to fix a concrete set of failing cases in code or a guardrail/classifier/filter/prompt/API the user
owns — a red-team catalogue, or the failing tests from a CI run — driving the open-class count to zero
without breaking what worked. A class is the root-cause group the loop closes as a unit (a red-team
technique, or a CI failure area / test class).
Default: pick the mode that matches the source (oracle for red-team, tests for CI/CD). Escape hatch:
in oracle mode with no separate functional test suite, the <holdout> alone is the regression guard;
in tests mode the suite's own previously-passing tests are the guard. Not for finding new failures (run
red-team), and not for editing the ground truth (the oracle, the tests, or the holdout).
What ships with it
4 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.
- 6d ago First seen · 198 lines · 201 tokens per session scan A cf9ece9f5f2a
blue-team is a skill published in the GitHub repository gaasher/Agent-Loop-Skills (163 stars, last pushed 2mo ago), licensed MIT. It adds 201 tokens to every session and 3,658 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
coral-debug
Verify and debug changes to CORAL itself — smallest reproduce loop per area (grader / daemon / CLI / hooks / manager / workspace / hub / template / config / web), where to look when something breaks (hung graders, agent restart loops, stalled agents, missing heartbeat actions, corrupted shared state, broken worktree…
autoresearch
Run a subagent-first structured improve-verify loop in OpenCode. Activate with /autoresearch or specialized modes like /autoresearch:plan, /autoresearch:debug, /autoresearch:fix, /autoresearch:learn, /autoresearch:predict, /autoresearch:scenario, /autoresearch:security, /autoresearch:ship. Supports recursive…
wrong-number-debugging
Use the moment a computed result looks wrong, surprising, suspicious, or "off" — a total that doesn't reconcile, revenue that tripled after a join, a mean that moved, a coefficient with the wrong sign, a count that's too high or too low, a metric that disagrees with another team's. Bisects the data pipeline to find…
postgres-diagnostics
Diagnose PostgreSQL health and performance using the read-only pgbot tool. Use for slow databases, expensive queries, unused indexes, disk usage, bloat, autovacuum, vacuum health, and configuration questions.
experiment-iterative-coder
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent…
experiment-craft
Use this skill when the user wants to debug, diagnose, or systematically iterate on an experiment that already exists, or when they need a structured experiment log for tracking runs, hypotheses, failures, results, and next steps during active research. Apply it to underperforming methods, training that will not…