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/ashkaan/contextium/implementnpx skills add Ashkaan/contextium --skill implementgit clone --depth 1 https://github.com/Ashkaan/contextiumWhat 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 | $0.00038 | $0.03532 |
| Opus 5 | $0.00019 | $0.01766 |
| Sonnet 5 | $0.00008 | $0.00706 |
| Haiku 4.5 | $0.00004 | $0.00353 |
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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement — SPEC-Driven Executor
The "do" verb of the loop. A prior session used /project to think and write a lean SPEC; this
session executes it. Validation loops catch mistakes early: run checks after every change, fix issues
immediately, never accumulate broken state.
Start in a fresh context
A session that wrote the plan is invested in it. It defends the choices it made while thinking instead of building cleanly to what the SPEC actually says. A fresh session has no such attachment — it reads the contract and implements it honestly.
So before you run /implement: open a new tab (or clear the context), then reload the SPEC from disk.
Nothing enforces this. It is a discipline you follow because it is the whole point of separating the
think and do verbs. Skip it and you lose that benefit.
load — read the SPEC
The argument is either a project name/slug or a SPEC-file path.
- If the argument resolves to an existing file path, use it directly.
- Otherwise treat it as a project slug — find
projects/*/{date}_<slug>/(any date prefix). - Inside the matched folder, find
*.spec.md:
| Match shape | Behavior |
|---|---|
| 0 SPEC files | HALT: "no SPEC in <project> — run /project <project> to write one first." |
| 1 SPEC file | Use it. |
| Multiple SPEC files | Pick the most-recent with no sibling *-report.md (not yet implemented). Still ambiguous → AskUserQuestion listing them. |
| No project matches the slug | HALT: "no project matches <name>" + list nearest slugs. |
Then read the SPEC. It follows the lean 4-section template (.claude/templates/spec-lean.md):
- § 1 — Ask — the verbatim ask. This is what you check the finished work against; it informs Verify Assumptions and the mechanism-match line.
- § 2 — Behavior — the behavior contract, including boundary cases (0/1/empty/max/error per
@rule:boundary-inputs). - § 3 — Files — files to create/change, patterns to mirror, downstream consumers to update in the
same pass (nothing deferred, per
@rule:no-deferral). - § 4 — Done — the exact commands to run and the output that means success, including the end-to-end check.
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.
- yesterday First seen · 247 lines · 38 tokens per session scan A d6c03cca19fd
implement is a skill published in the GitHub repository Ashkaan/contextium (32 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 3,532 once invoked, about $0.0002 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 skills, from other repositories
sovereign-economics-engine
Unified business model evaluator, client filter, pricing engine, and distribution architect. Absorbs 31 business + 8 marketing + 13 content + 2 acquisition protocols.
therapeutic-ifs
Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.
bionic-decision-engine
Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.
statistical-analysis
Structured pipeline for statistical analysis deliverables — SPSS, R, Python. Covers reliability, chi-square, correlation, regression, assumption checking, and client-ready reporting.
decision-journal
Unified decision lifecycle: Pre-decision logging, post-decision review, failure classification, and calibration tracking. Absorbs: post-mortem-engine.