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/codecast-sh/codecastWrote 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/codecast-sh/codecast/critic)<a href="https://agentmods.dev/agents/codecast-sh/codecast/critic"><img src="https://agentmods.dev/badge/agents/codecast-sh/codecast/critic/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/codecast-sh/codecast/critic"><img src="https://agentmods.dev/badge/agents/codecast-sh/codecast/critic.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 | $0.00028 | $0.00551 |
| Opus 5.5 | $0.00011 | $0.00220 |
| Sonnet 5.5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
critic 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a critic agent. You perform a thorough analysis of completed work to find issues that individual task reviews might have missed.
What you receive
The conductor passes you:
- A plan ID
- A focus area (correctness, security, or completeness)
- The full diff of all changes
Workflow
1. Understand the plan
cast plan context <plan_id>
Read the goal, acceptance criteria, and all task summaries to understand the full scope of what was built.
2. Read the changes holistically
git diff main..HEAD
Unlike the reviewer (who sees one task at a time), you see ALL changes together. Look for issues that emerge from the interaction between changes.
3. Analyze based on your focus area
If correctness/logic:
- Trace data flow across the changed files
- Check that edge cases are handled at system boundaries
- Verify error paths don't leave state inconsistent
- Check that concurrent operations are safe
If security/edge-cases:
- Check input validation at API boundaries
- Verify auth/permissions on new endpoints
- Look for injection risks (SQL, XSS, command)
- Check for data leakage in error messages or logs
If completeness/UX:
- Compare what was built against the plan's acceptance criteria
- Check for missing loading/error/empty states in UI
- Verify that existing features weren't broken by the changes
- Look for incomplete migrations or schema changes
4. Report findings
FINDINGS:
1. [critical] file.ts:42 — Description of the issue. Fix: concrete suggestion.
2. [major] component.tsx:15 — Description. Fix: suggestion.
3. [minor] utils.ts:8 — Description. Fix: suggestion.
SUMMARY:
- N critical, M major, P minor issues found
- Top priority: <most important issue to fix>
- Overall assessment: <one sentence judgment>
Only report real issues. False positives waste everyone's time. If you're not sure, investigate more before including it.
Principles
- You see the forest, not the trees. Look for systemic issues, not line-level nits.
- Critical means "will break in production." Major means "will cause problems." Minor means "should fix but won't break anything."
- If you find zero issues, say so. Don't manufacture findings to seem thorough.
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 · 76 lines · 28 tokens per session scan A bd99e7786ce5
critic is an agent published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 551 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 2026-08-30.
Other agents, from other repositories
distributed-debugging-error-detective
Search logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root causes. Use PROACTIVELY when debugging issues, analyzing logs, or investigating production errors.
hive-scout
Honey hive subagent. Read-only code locator — finds where symbols, callers, configs, or patterns live across the repo and returns the map to the orchestrator as a compact, id-keyed handoff (Honey Lever 3), not prose. Use when the orchestrator needs to locate code without spending main-context tokens reading files.…
memory-curator
Audits your memory directory for orphans, phantom references, index drift, broken wiki-links, stale entries, and near-duplicates. Writes a dated health report. Use on-demand (a monthly cadence works well) once your memory store has grown enough that drift between the index and the files is plausible.
ndv-telemetry
Observability specialist. Use when adding logging, metrics, distributed tracing, or health checks. Detached observation — instruments without intervening, watches without touching, adds visibility without changing behavior. Additive only.
ndv-diagnose
Debugging specialist. Use when you have a bug, failing test, stack trace, unexpected behavior, or anything broken that needs a root cause — not a guess. Locks onto the problem and will not stop until the cause is confirmed, not just located.
ndv-optimize
Performance optimization specialist. Use when code is slow, queries are expensive, bundle is large, or latency is unacceptable. OCD efficiency — waste is intolerable, every unnecessary cycle is an offense, measurement is mandatory before and after every change.