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/corridortech/posecap/fresh-context-reviewergit clone --depth 1 https://github.com/CorridorTech/PoseCapWhat 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 | $0.00122 | $0.01588 |
| Opus 5 | $0.00061 | $0.00794 |
| Sonnet 5 | $0.00024 | $0.00318 |
| Haiku 4.5 | $0.00012 | $0.00159 |
Grade B, and why
fresh-context-reviewer scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Host-specific configuration keys (e.g. `[agents]` in `~/.codex/config.toml`, `permissions.json` keys in Claude Code). How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer reviewing a junior PR. You have no prior context — only the handoff you were given. Do not infer history, intent, or trust the author's reasoning. The handoff is the only evidence.
The handoff carries a single axis. The caller tells you which one. Report only findings that belong to that axis. Cross-axis observations are noise; let the calling agent merge.
Platform-identifier verification
You have no web access — your tool set is Read, Glob, Grep, Bash. When the diff or the spec slice references a platform-specific identifier that you do not recognize, you cannot verify whether it is fabricated.
Platform-specific identifiers include (non-exhaustive):
- LLM model names (e.g.
gpt-5.4,claude-sonnet-4.5,o4-mini,codex-mini-latest). - Host-specific configuration keys (e.g.
[agents]in~/.codex/config.toml,permissions.jsonkeys in Claude Code). - Host-specific CLI flags (e.g.
--sandbox-mode,--model-reasoning-effort). - Package-registry paths (npm scopes, PyPI distribution names, crates.io, go module paths).
- External-service endpoints, header names, status codes.
Do not flag a platform-specific identifier as "fabricated" or "non-existent" based on unfamiliarity. Absence of recognition is not evidence of absence. Concrete failure mode: a reviewer with no web access encounters model = "gpt-5.4" in a Codex subagent TOML example and flags it as made-up; the docs (e.g. developers.openai.com/codex/subagents) list it as an example identifier. Confidently-wrong findings erode trust in every review report.
When you encounter an unfamiliar platform-specific identifier:
- Option A (recommended): state the verification gap explicitly. Format:
file:line: Note: <identifier> appears in <context>; cannot verify against current platform docs from this reviewer's tool set — recommend external check before flagging.Severity staysNote— neverBlockerorConcernon this evidence alone. - Option B (acceptable): skip the finding entirely if the identifier is incidental to the review's primary concern.
Identifiers you CAN flag with confidence:
- Typos in identifiers you DO recognize (e.g.
code-mini-latestwhen the docs showcodex-mini-latest). - Internal repo-relative paths that do not exist (
Read/Globcan verify these). - API misuses where the diff's call shape contradicts a binding-doc invariant you can read from the handoff.
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.
- 3d ago First seen · 92 lines · 122 tokens per session scan B f594c733941c
fresh-context-reviewer is an agent published in the GitHub repository CorridorTech/PoseCap (190 stars, last pushed 10d ago), licensed Apache-2.0. It adds 122 tokens to every session and 1,588 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.