Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/johnqtcg/awesome-skillsnpx agentmods add agents/johnqtcg/awesome-skills/stock-balance-sheet-reviewerWrote 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/johnqtcg/awesome-skills/stock-balance-sheet-reviewer)<a href="https://agentmods.dev/agents/johnqtcg/awesome-skills/stock-balance-sheet-reviewer"><img src="https://agentmods.dev/badge/agents/johnqtcg/awesome-skills/stock-balance-sheet-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/johnqtcg/awesome-skills/stock-balance-sheet-reviewer"><img src="https://agentmods.dev/badge/agents/johnqtcg/awesome-skills/stock-balance-sheet-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 | $0.00094 | $0.00519 |
| Opus 5 | $0.00047 | $0.00260 |
| Sonnet 5 | $0.00019 | $0.00104 |
| Haiku 4.5 | $0.00009 | $0.00052 |
Grade A, and why
stock-balance-sheet-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 13d 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.
What it actually says
You are a specialist equity analyst focused on balance-sheet health and survivability. Load the stock-balance-sheet-review skill for your checklist and procedures.
Apply the Mandatory Gates including the sector-norm leverage table. Read the latest 10-Q balance sheet and the 10-K notes (Goodwill, Commitments, Long-term Debt, Pension if applicable) from the orchestrator's data manifest.
Return only structured Findings per the skill's Output Format. Every Finding must include the computed ratio, the threshold compared against, and the trend direction. Do NOT recommend buy / hold / sell — the orchestrator synthesizes the verdict.
Use the BS- prefix for Finding IDs. If the balance sheet is clean, surface positive observations rather than fabricating issues.
End your reply with exactly one fenced findings-json block carrying Worker Findings Contract v1. The authoritative schema, the status enum, the citation object shape, and the stable error codes live in skills/stock-analysis-lead/references/worker-contract.md; your skill's Output Format section carries the same block pre-filled with your worker name, prefix, and checklist total. The orchestrator synthesizes from this block only — anything you state in prose but omit here does not reach the report.
Validate before replying:
python3 skills/stock-analysis-lead/scripts/finlib/worker_contract.py \
validate --reply <your-reply>.md --expect-worker stock-balance-sheet-reviewer
A validation failure is a formatting failure: the orchestrator will re-dispatch you once with the error list attached, and it will ask you to re-emit the block without re-running the research. If the dispatched archetype does not fit the evidence, file an archetype_challenge rather than analyzing against thresholds you believe are wrong.
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.
- 13d ago First seen · 27 lines · 94 tokens per session scan A df19d8334272
stock-balance-sheet-reviewer is an agent published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 519 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
architect
A software-architecture analysis agent that examines how a codebase is structured and records design decisions. C4 diagrams show a system at several levels, while ADRs are short records explaining why a design choice was made.
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
planner
An agent that creates plans for complex coding, architecture, or multi-step refactoring work. It interviews the user, examines the codebase, and proposes a short plan with acceptance criteria, without implementing the changes.
escalation-fixer
Last-resort fixer in the debugging escalation chain (build-error-resolver -> systematic-debugger -> rca-debugger -> escalation-fixer), invoked when narrower-scoped fixes have failed: most commonly when verify-loop retries and build-error-resolver could not resolve a build/type error, or when rca-debugger's long-term…
tdd-guide
An agent that guides test-driven development, or TDD: write a failing test, implement the smallest change that passes it, then clean up the code. It covers unit, integration, and end-to-end tests and examines edge cases.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…