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 iampantherr/SecureContext --skill writing-skillsgit clone --depth 1 https://github.com/iampantherr/SecureContextWrote 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/iampantherr/securecontext/writing-skills)<a href="https://agentmods.dev/skills/iampantherr/securecontext/writing-skills"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/writing-skills/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/iampantherr/securecontext/writing-skills"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/writing-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 22 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00102 | $0.02201 |
| Opus 5 | $0.00051 | $0.01100 |
| Sonnet 5 | $0.00020 | $0.00440 |
| Haiku 4.5 | $0.00010 | $0.00220 |
Grade A, and why
writing-skills 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 9d 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.
curl -s -X POST \ How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing skills
This is the meta-skill: it teaches an agent how to write other skills, and it ships a linter + admission-preview tool to catch errors before the admission gate does.
When to use
Trigger phrases:
- "Write a skill for X"
- "Create a skill that does Y"
- "Scaffold a new skill"
- "Help me author a skill"
- "How do I make a skill that …"
- Anywhere the operator asks for a new
~/.claude/skills/<name>/or<project>/.claude/skills/<name>/.
DO NOT use this for:
- Editing an existing skill (use the dashboard "Edit frontmatter" button instead).
- Documenting facts (those go in
references/orzc_remember, not in a skill). - One-off tasks (if the procedure isn't worth running ≥3 times, don't encode it as a skill).
Procedure
Step 1 — confirm the four invariants are satisfiable
Before writing a single line, talk to the operator and confirm:
- Trigger — can you write a one-sentence "use this whenever X" rule? If not, stop. The user's request is for a one-off, not a skill.
- Procedural — does the work decompose into 3–7 ordered steps? If not, the procedure is either too vague or too narrow.
- Single-responsibility scripts — does each step map to one bundled script (or one in-line Bash command)? If a step needs a script that does five things, split it.
- Project-config-aware — does the procedure touch project-specific
values (paths, names, ports)? If yes, the script must read those from
<project>/.<skill-name>-config.jsonorzc_remember, never hardcoded.
If any of the four is shaky, stop and discuss with the operator before generating any files.
Step 2 — decide the scope (global vs project-local)
This decision matters. Get it wrong and the skill either pollutes the global namespace with project-specific assumptions, or it gets duplicated across N projects when one global skill + per-project config would have sufficed.
Decision matrix — answer these questions:
| Question | If YES → | If NO → |
|---|---|---|
| Does the procedure touch only standard files (package.json, CHANGELOG.md, README.md, pyproject.toml, *.test.js)? | Maybe global | Maybe project |
| Does the procedure have ZERO hardcoded paths, project names, ports, DB IDs, internal URLs? | Maybe global | Project |
| Has this exact pattern appeared in ≥2 distinct projects already? | Strong global | Project (for now) |
| Does the procedure reference project-specific files (HANDOFF.md, STRATEGY.md, internal-policies.md)? | Project | Maybe global |
| Does the procedure encode a team-specific convention (commit format, branch naming, deploy URL)? | Project | Maybe global |
| Does the procedure only fire in one repo so far? | Project (promote later) | Maybe global |
What ships with it
6 files 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.
- 9d ago First seen · 221 lines · 102 tokens per session scan A 1c08ff0d63d2
writing-skills is a skill published in the GitHub repository iampantherr/SecureContext (8 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 2,201 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
release-init
Detect project type and generate a tailored project-level /release skill. Run once per project to set up releasing.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…