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 nearform/lastlight --skill security-feedbackgit clone --depth 1 https://github.com/nearform/lastlightWrote 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/nearform/lastlight/security-feedback)<a href="https://agentmods.dev/skills/nearform/lastlight/security-feedback"><img src="https://agentmods.dev/badge/skills/nearform/lastlight/security-feedback/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/nearform/lastlight/security-feedback"><img src="https://agentmods.dev/badge/skills/nearform/lastlight/security-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 36 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00036 | $0.02176 |
| Opus 5.5 | $0.00014 | $0.00870 |
| Sonnet 5.5 | $0.00007 | $0.00435 |
| Haiku 4.5 | $0.00004 | $0.00218 |
Grade A, and why
security-feedback scanned grade A 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 1mo 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.
GitHub operations via `github_*` MCP tools only — never `gh` CLI, `curl`, or raw HTTP. How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Feedback
A maintainer commented on a security-labelled issue — almost always a per-run
security scan summary (one issue per scan, a task-list of findings). Based on
the comment, either:
- Break selected findings into individual issues (each can later feed
build). Primary flow. - Record a suppression in
SECURITY.md(accepted risk / false positive). - Reply for discussion, or ignore noise.
The parent issue's grammar is the contract defined in
skills/security-review/references/issue-format.md. This skill is staged into its
own workspace and cannot read that file, so it carries its own copy of the
row/severity regex below — if you change the grammar, update both in lockstep.
Context
context.repo—owner/namecontext.issueNumber— the security summary issue (parent)context.commentBody— the triggering commentcontext.sender— the commenter's GitHub login
The parent body is not passed — fetch it at step 1.
1. Fetch and parse the parent issue
github_get_issue({ owner, repo, issue_number: issueNumber }).
Version check. The body MUST start with <!-- lastlight-security-scan-version: 1 -->.
If the marker is missing or the version isn't 1, reply: "Unknown scan-summary
format — this skill is at version 1 but the parent reports a different version.
Ask the maintainer to re-run @last-light security-review." Do not parse further.
Parse each finding row with this canonical regex (all three states):
/^- \[([ x])\] <!-- item:(\d+) fp:([0-9a-f]{8,}) --> (?:~~)?\*\*(.+?)\*\* — `([^`]+):(\d+)` \(([a-z][a-z0-9-]*) · `([^`]+)`\)(?:~~ → #(\d+))?$/m
Captures: checkbox ( /x), item, fp, title, file, line, tool,
rule, and subIssueNumber (only when already broken out). Derive per row:
| Derived | Definition |
|---|---|
alreadyBrokenOut |
subIssueNumber != null — turned into a sub-issue on a prior run |
userTicked |
checkbox === "x" && !alreadyBrokenOut — the maintainer ticked the box, selecting it |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 181 lines · 36 tokens per session scan A 739e5bb6d514
security-feedback is a skill published in the GitHub repository nearform/lastlight (41 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 2,176 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca
Use when the user asks to run an Orca flow (e.g. "use orca to implement …"), or when delegating a well-defined implementation task to Orca's autonomous multi-agent flow — a headless plan-code-review CLI to hand a coding task to instead of implementing it yourself.
example-skill
Counts lines, words, and bytes in a text file using the bundled count.sh script. Use when asked to count/measure a file's size in these terms.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
rowan
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.