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 makifbaysal/tasktrooper --skill security-reviewgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/security-review)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/security-review"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/security-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/makifbaysal/tasktrooper/security-review"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/security-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 | $0.00041 | $0.01541 |
| Opus 5.5 | $0.00016 | $0.00616 |
| Sonnet 5.5 | $0.00008 | $0.00308 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
security-review scanned grade A with 2 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- ❌ `exec.Command("curl", "-H", "Authorization: Bearer "+token, url)` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Injection sinks** — string-built SQL, `exec.Command("sh","-c",…)` / `child_process.exec`, template `|safe`, `dangerouslySetInnerHTML`, `v-html`. How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review
Overview
Security is not a separate pass over the whole repo — it is one more lens on the diff (code_review) or the design (analysis) you are already reading. Report only what is reachable by an attacker; a theoretical issue with no path to it is noise that trains people to skip your findings.
1. Risk Tier First
- High — auth, payments, admin actions, file upload, outbound URL fetch, anything that calls an LLM with tool access. Run the full checklist below.
- Medium — user data, external API calls. Run Injection, Authorization, Exceptional Conditions, Secrets.
- Low — pure UI, utilities, pure config/copy. Run Secrets and Supply Chain only.
2. Map the Attack Surface (of the diff, not the repo)
List, from the diff: every new input (params, headers, body, path segment, uploaded file, webhook payload, LLM output used downstream), every new or changed query, every auth/authorization check, every outbound call, every secret touched.
3. Report Only Attacker-Reachable Findings
Trace the value to its source with grep_code/expand_symbol_context before flagging it. Not attacker-controlled: config values, environment variables, constants, server-set values, test fixtures. Not a finding: framework auto-escaping doing its job (React {x}, an ORM's parameterized query) — that is the control working, not a gap.
4. Checks
Authorization per new route — does it carry the same middleware as its neighbours, and does the query filter by owner/tenant (IDOR)?
- ❌
func (h *Handler) GetInvoice(w, r) { id := r.PathValue("id"); inv, _ := h.repo.Get(ctx, id); json.NewEncoder(w).Encode(inv) }— any authenticated user reads any invoice by guessing an id. - ✅
inv, err := h.repo.Get(ctx, id); if inv.OrgID != authctx.OrgID(ctx) { return ErrForbidden }— the query result is checked against the caller's scope before it is returned.
Injection sinks — string-built SQL, exec.Command("sh","-c",…) / child_process.exec, template |safe, dangerouslySetInnerHTML, v-html.
- ❌
db.Exec(fmt.Sprintf("SELECT * FROM tasks WHERE title = '%s'", title)) - ✅
db.Exec("SELECT * FROM tasks WHERE title = $1", title)
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.
- 8d ago First seen · 84 lines · 41 tokens per session scan A 80c03ff8f226
security-review is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 1,541 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
code-review
Use this skill to systematically review code changes for correctness, security, performance, maintainability, and test coverage. Activates after implementation, before merging, or when asked to review a pull request or code change. Produces a structured review report with findings categorized by severity.
tdd
Use this skill to practice test-driven development — writing tests before implementation, using tests to drive design, and validating implementation against pre-written tests. Activates when implementing new functionality, refactoring code, or fixing bugs where regression coverage is needed.
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
paperclip-create-agent
Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.