Borrowing it
Nothing to install: this file belongs to CorridorTech/PoseCap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CorridorTech/PoseCap/main/.claude/agents/fresh-context-reviewer.mdgit clone --depth 1 https://github.com/CorridorTech/PoseCapWrote 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/corridortech/posecap/fresh-context-reviewer)<a href="https://agentmods.dev/agents/corridortech/posecap/fresh-context-reviewer"><img src="https://agentmods.dev/badge/agents/corridortech/posecap/fresh-context-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/corridortech/posecap/fresh-context-reviewer"><img src="https://agentmods.dev/badge/agents/corridortech/posecap/fresh-context-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 | $0.00122 | $0.01588 |
| Opus 5.5 | $0.00049 | $0.00635 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (265 stars, last pushed 3d ago), licensed Apache-2.0. It adds 122 tokens to every session and 1,588 once invoked, about $0.0005 per session on Opus 5.5. 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
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.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
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.