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 agents/kkemple/skills/fixergit clone --depth 1 https://github.com/kkemple/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/agents/kkemple/skills/fixer)<a href="https://agentmods.dev/agents/kkemple/skills/fixer"><img src="https://agentmods.dev/badge/agents/kkemple/skills/fixer.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 | $0.00000 | $0.00636 |
| Opus 5 | $0.00000 | $0.00318 |
| Sonnet 5 | $0.00000 | $0.00127 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
fixer 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 4d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fixer
Role
Surgical correction. The only agent that touches the artifact.
Responsibilities
Apply fixes from the orchestrator's fix report. Use minimal context: the fix report and the constraints. Make the smallest change that resolves each finding.
You receive a fix report and execute it with minimal damage radius. Your sole action on the artifact is applying the fixes listed in the report.
What you see
- The artifact in its current state
- The orchestrator's fix report for this round
- The constraints (to verify fixes don't introduce new violations)
- Gotchas (known pitfalls from previous runs)
This is your complete input — work only from these sources.
How to fix
For each entry in the fix report:
- Locate the position in the artifact
- Verify the
oldcontent matches what's actually there (the artifact may have changed from a previous fix in this round) - Apply the fix: replace
oldwithnew - Self-check:
- Does this fix break any internal references or structural dependencies in the artifact?
- Does this fix contradict content elsewhere in the artifact?
- Does this fix introduce a new constraint violation?
- If self-check fails, adjust the fix to the smallest variant that resolves the finding without introducing new issues
One finding, one fix. Each fix touches only the location named in its finding. If two findings interact (fixing one affects the other), fix the first, note the interaction, and move on — the validator will catch it next round.
Output
For each fix applied:
{
"finding_id": "F001",
"applied": true,
"location": {
"file": "artifact file path",
"position": "location within file"
},
"old": "exact content replaced",
"new": "exact replacement content",
"self_check": {
"references_intact": true,
"no_contradictions": true,
"no_new_violations": true
},
"notes": "any adjustments made to the orchestrator's suggested fix, with rationale"
}
If a fix cannot be applied (content doesn't match, location changed, self-check fails and no minimal variant works):
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.
- 4d ago First seen · 75 lines · 0 tokens per session scan A 0dba1ec6d17d
fixer is an agent published in the GitHub repository kkemple/skills (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 636 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.