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 agentmods add skills/justomsharma/github-resume-assistant/implementnpx skills add justomsharma/github-resume-assistant --skill implementgit clone --depth 1 https://github.com/justomsharma/github-resume-assistantWhat 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 | $0.00060 | $0.00419 |
| Opus 5 | $0.00030 | $0.00210 |
| Sonnet 5 | $0.00012 | $0.00084 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
implement 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 2d 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
implement
Build the code for the approach approved in /plan-first. If no approach has been
validated yet, STOP and run /plan-first first.
Before writing
- Re-read the relevant parts of
docs/ARCHITECTURE.md(where code goes) anddocs/CODING_PRACTICES.md(how code is written). - Confirm the target files match the approved plan.
While writing
Follow CODING_PRACTICES.md strictly:
- Full type hints on every function.
- Keep
core/free of MCP imports — pure logic only. - Secrets only through
config.py; never hardcode keys. - Specific error handling on external calls; add retry/backoff in
clients/. - Reuse existing models in
core/models.py; add to them rather than duplicating. - Keep MCP tool functions thin: validate → call
core/→ format output. - Match surrounding style. No dead code, no leftover debug prints.
Scope discipline
- Build only what the approved approach covered. If you discover the plan was
wrong or incomplete, STOP and go back to
/plan-first— don't silently expand scope.
Self-check before handing off
- Code matches the approved approach
- Fully typed; would pass
ruffandmypy - No secrets, no bare
except, no dead code -
core/has no MCP imports - New logic lives in the layer ARCHITECTURE.md assigns it to
Handoff
Once the code is written → hand off to /test to add and run tests.
Do NOT commit yet.
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.
- 2d ago First seen · 45 lines · 60 tokens per session scan A 6c3c6b87a903
implement is a skill published in the GitHub repository justomsharma/github-resume-assistant (0 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 419 once invoked, about $0.0003 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
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
concept-synthesis
Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint.