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 skills add marcoguillermaz/Tierward --skill context-reviewgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/skills/marcoguillermaz/tierward/context-review)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/context-review"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/context-review/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/skills/marcoguillermaz/tierward/context-review"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/context-review.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 | $0.00081 | $0.00881 |
| Opus 5 | $0.00041 | $0.00441 |
| Sonnet 5 | $0.00016 | $0.00176 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
context-review 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 10d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a context file reviewer. Run exactly the three checks below and return the results. Do not interpret, do not suggest fixes - report findings only.
C1 - Credential patterns in MEMORY.md
Grep the auto-memory file at ~/.claude/projects/[current-project-hash]/memory/MEMORY.md for token/secret patterns.
Pattern to search:
sk_live_[a-zA-Z0-9]{10,}|api_key.*=.*[a-zA-Z0-9]{10,}|password.*=.*[a-zA-Z0-9]{8,}|token.*=.*[a-zA-Z0-9]{10,}
PASS: 0 matches, or all matches are placeholder strings with no actual token value (e.g. sk_live_... with literal dots, or property names in code examples).
FAIL: any match that looks like a real token value (8–10+ alphanumeric chars after the pattern).
Note: must_change_password, password: string, property names in code examples are NOT credentials - the grep targets actual value strings.
Note: the tier-l Stop closure hook (.claude/settings.json) mirrors this exact credential pattern to mechanically scan the block diff at completion time (a different surface than this MEMORY.md scan). The two share one pattern by design - if you change the regex here, update the hook too, and vice versa.
C2 - Unresolved placeholders in active files
Scope: every non-code-block line in CLAUDE.md and .claude/rules/pipeline.md.
Grep both files for the pattern [A-Z_]{3,} wrapped in square brackets:
\[[A-Z_]{3,}\]
PASS: 0 matches, or all matches are inside fenced code blocks that are intentional examples (e.g. spec templates, commit message examples). FAIL: any match in a non-code-block line - this indicates an unfilled wizard value.
C3 - Field name staleness
Identify the most recent schema migration or schema definition file in this project (glob common migration patterns: migrations/*.sql, prisma/schema.prisma, db/migrate/*.rb, drizzle/*.ts, */migrations/*.py, alembic/versions/*.py, Migrations/*.cs, *.xcdatamodeld - take the most recently modified).
If found: extract all column/field names added, renamed, or dropped in that file. Cross-reference against any mentions of those names in CLAUDE.md.
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.
- 10d ago First seen · 80 lines · 81 tokens per session scan A 2d6de444322b
context-review is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 881 once invoked, about $0.0004 per session on Opus 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 skills, from other repositories
context-recovery
Recovers project handoff context from local Codex, Claude Code, Gemini, CodeBuddy, and codexmate-derived sessions. Use when the user asks what happened in prior project/PR/branch/file/error work, needs a handoff brief, wants old decisions or validations recovered, or asks to summarize cross-session project activity…
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
harness-engineering
Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
init
Turn on Rekal memory in the current repository by running rekal init. Use when the user asks to initialize or set up Rekal here, or when a rekal command reported the repository is not initialized. Once per repository. Do not offer this merely because a repo lacks a .rekal/ store — most repos do not want one.
install
Install the Rekal binary on this machine. Use when rekal is not on PATH — a command reported command not found — or when the user asks to install Rekal. Once per machine, not per repository; to set up a repo that already has the binary, use the init skill instead.