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 jrjsmrtn/tlx --skill spec-driftgit clone --depth 1 https://github.com/jrjsmrtn/tlxWrote 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/jrjsmrtn/tlx/spec-drift)<a href="https://agentmods.dev/skills/jrjsmrtn/tlx/spec-drift"><img src="https://agentmods.dev/badge/skills/jrjsmrtn/tlx/spec-drift.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00948 |
| Opus 5 | $0.00032 | $0.00474 |
| Sonnet 5 | $0.00013 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
spec-drift 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 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.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Drift Detection
Detect when implementation code has diverged from its formal TLX spec, so specs stay in sync with the codebase.
When to Use
- Before a release — verify all specs are current
- After a refactoring sprint — check if specs need updating
- In CI — flag PRs that change source without updating specs
- During code review — "did you update the spec?"
Step 1: Find Spec Files with Source References
Scan for spec files that declare a # Source: header:
grep -rl "# Source:" specs/ lib/specs/ test/specs/
For each spec file, extract:
- The
# Source:path (implementation file) - The
# ADR:number (if present) - The spec module name
Step 2: Compare Timestamps
For each spec/source pair, check git modification dates:
# Last modification of source
git log -1 --format="%ai" -- lib/my_app/reconciler.ex
# Last modification of spec
git log -1 --format="%ai" -- specs/reconciler_spec.ex
If the source is newer than the spec, the spec may be stale.
Step 3: Re-Extract and Diff Structure
For stale specs, re-run the appropriate extractor and compare the extracted structure against the existing spec:
# Re-extract current structure
mix tlx.gen.from_gen_server MyApp.Reconciler --format codegen --output /tmp/current.ex
# Diff against existing spec
diff specs/reconciler_spec.ex /tmp/current.ex
Look for:
- New states/fields: added in source but not in spec
- Removed states/fields: deleted from source but still in spec
- New callbacks/actions: new handle_call/cast/info clauses
- Changed transitions: different field updates in return tuples
Step 4: Generate Drift Report
Present findings as a table:
Spec Source Status
──────────────────────────────────────────────────────────────────────
specs/reconciler_spec.ex lib/my_app/reconciler.ex ⚠ STALE
Source modified: 2026-03-28 Spec modified: 2026-03-15
Diff: +2 new handle_call clauses, +1 new field (retry_count)
specs/orchestrator_spec.ex lib/my_app/orchestrator.ex ✓ OK
Source modified: 2026-03-10 Spec modified: 2026-03-12
specs/fleet_live_spec.ex lib/my_app_web/fleet_live.ex ⚠ STALE
Source modified: 2026-03-25 Spec modified: 2026-03-01
Diff: +3 new handle_event clauses
──────────────────────────────────────────────────────────────────────
Stale: 2/3 Up to date: 1/3
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 · 123 lines · 63 tokens per session scan A 0365bf2de6ad
spec-drift is a skill published in the GitHub repository jrjsmrtn/tlx (10 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 948 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…