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.
git clone --depth 1 https://github.com/knitli/toolshedWrote 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/knitli/toolshed/ctx-fix)<a href="https://agentmods.dev/commands/knitli/toolshed/ctx-fix"><img src="https://agentmods.dev/badge/commands/knitli/toolshed/ctx-fix/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/commands/knitli/toolshed/ctx-fix"><img src="https://agentmods.dev/badge/commands/knitli/toolshed/ctx-fix.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00644 |
| Opus 5.5 | $0.00009 | $0.00258 |
| Sonnet 5.5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
ctx-fix 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ctx:fix — Auto-Reconcile Context Issues
Fix staleness and drift issues found by /ctx:check and /ctx:drift. Operates interactively: proposes each fix and waits for approval before applying.
Arguments
$ARGUMENTS
- No arguments: run a full audit, then propose fixes for all issues found.
- File paths (e.g.,
/ctx:fix CLAUDE.md): audit and fix issues only in the named files. - Ecosystem names (e.g.,
/ctx:fix serena): audit and fix issues only in files belonging to those ecosystems. - Issue types (e.g.,
/ctx:fix broken,/ctx:fix versions): run a full audit but only propose fixes for the specified issue category (broken, stale, versions, contradictions, gaps, orphaned).
Instructions
First, run a full audit (/ctx) to identify all issues — scoped to the user's arguments if provided. Then work through fixes in priority order.
Fix priority
- Broken claims (❌) — References to files, symbols, or commands that don't exist. These actively mislead agents.
- Version mismatches — Wrong version numbers are easy to fix and high-impact.
- Contradictions between files — Pick the authoritative source and update the others.
- Gaps in secondary files — Where Serena/Gemini/Cursor memories are missing information that CLAUDE.md or the constitution has.
- Orphaned planning docs — Suggest archival or deletion.
How to fix
For each fixable issue, propose the specific edit:
- Show the current text (with file path and line number)
- Show the proposed replacement
- Explain why this is the correct fix
- Ask for approval before applying
For version/path/symbol fixes: The codebase is authoritative. Update the context file to match reality.
For contradictions across files: Identify the most authoritative source (usually: constitution > CLAUDE.md > AGENTS.md > tool-specific memories > planning docs). Update less-authoritative files to match.
For orphaned docs: Propose moving to an archive/ directory or deletion. Never delete without explicit approval.
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 · 61 lines · 23 tokens per session scan A 7c22174eee43
ctx-fix is a command published in the GitHub repository knitli/toolshed (1 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 644 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
skillrx
Scan AI agent plugin or skill for malicious patterns before install.
memory-compact
Run a dry run first.
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.