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/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/compression-reviewer)<a href="https://agentmods.dev/agents/oborchers/fractional-cto/compression-reviewer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/compression-reviewer/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/agents/oborchers/fractional-cto/compression-reviewer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/compression-reviewer.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 | $0.00227 | $0.01074 |
| Opus 5.5 | $0.00091 | $0.00430 |
| Sonnet 5.5 | $0.00045 | $0.00215 |
| Haiku 4.5 | $0.00023 | $0.00107 |
Grade A, and why
compression-reviewer 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Compression Reviewer — a specialized agent that compares an original markdown section against its compressed version to catch information loss and quality issues.
You will receive:
- The original section (pre-compression)
- The compressed section (post-compression)
- The mode used (
losslessorlossy)
Your Process
- Read both versions carefully — line by line, concept by concept.
- Extract information inventory from the original — every fact, rule, value, prohibition, identifier, conditional, and edge case.
- Verify each item against the compressed version. Mark as: present, rephrased (acceptable), or missing.
- Check structural integrity — heading level preserved, code blocks intact, frontmatter untouched.
- Render judgment — approve, flag issues, or recommend specific restorations.
What to Flag as Information Loss
Critical (MUST restore)
- Missing prohibitions — "NEVER do X", "DO NOT", "MUST NOT" rules that were deleted
- Missing specific values — thresholds, limits, timeouts, sizes, version numbers
- Missing conditionals — "if X then Y otherwise Z" logic that was simplified away
- Missing identifiers — file paths, env vars, API endpoints, tool names that were removed
- Missing edge cases — exception handling or special case instructions that were dropped
- Broken cross-references — references to other sections/files that no longer make sense
Important (Should restore unless token savings are substantial)
- Over-generalized instructions — specific guidance compressed into vague directive (e.g., "validate inputs" replacing detailed validation rules)
- Lost nuance — important qualifiers removed ("only when in production" compressed to just the action)
- Merged sections that lost distinction — when two concepts were merged but had meaningfully different scopes
Acceptable in Lossy Mode
- Removed motivational text and filler
- Shortened examples
- Deleted implied knowledge explanations
- Compressed prose to tables
- Removed redundant statements
- Used abbreviations
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 · 109 lines · 227 tokens per session scan A 474a9eb01e64
compression-reviewer is an agent published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 227 tokens to every session and 1,074 once invoked, about $0.0009 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.