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 alebgl77/tierdecay --skill tierdecay-distillgit clone --depth 1 https://github.com/alebgl77/tierdecayWrote 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/alebgl77/tierdecay/tierdecay-distill)<a href="https://agentmods.dev/skills/alebgl77/tierdecay/tierdecay-distill"><img src="https://agentmods.dev/badge/skills/alebgl77/tierdecay/tierdecay-distill/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/alebgl77/tierdecay/tierdecay-distill"><img src="https://agentmods.dev/badge/skills/alebgl77/tierdecay/tierdecay-distill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00513 |
| Opus 5.5 | $0.00024 | $0.00205 |
| Sonnet 5.5 | $0.00012 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
tierdecay-distill 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 13d 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
TierDecay DISTILL (orchestrator only)
Executors never write .tierdecay/. Run this after VERIFY, once per task.
- Ledger row. One row per task in
.tierdecay/ledger.md(keep the last 50):date | class | predicted | executed | outcome | esc | playbook. For a measured ledger, prefertierdecay observe --observation row.json --append .tierdecay/ledger.md(validated, locked, atomic) or the MCPtierdecay_recordtool when the server runs with--allow-ledger-append true. - Referenced entry failed? Move it to QUARANTINE with a one-line cause;
the failed tier becomes its sticky
floor:. Never apply, export, or probe a quarantined entry until revised. - Probe passed?
hits +1. When hits reach 3 / 4 / 5 for the entry'srisk:0 / 1 / 2 (risk 3 never decays; norisk:= 2), rewriteprovenance:to the tier that passed and reset hits to 0. - Recertification passed? Set
epoch:to the current binding epoch,hits: 0. - Distill only after a T2/T3 success on a class that will recur: a
≤15-line entry with
provenance,risk,epoch,WHEN,DO,VERIFY. Decisions only — invariants, ordering, the trap — never diffs, secrets, or volatile values. If the lower tier already passes cold, routing alone captures the saving: do not distill. - Hygiene. Playbook hard cap 150 lines; evict lowest hits, oldest first.
Run
tierdecay status(ortierdecay_status) for owed bookkeeping andtierdecay export --format skills --out .agents/skillsto refresh skills.
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.
- 13d ago First seen · 32 lines · 59 tokens per session scan A e2f148f0eb82
tierdecay-distill is a skill published in the GitHub repository alebgl77/tierdecay (1 stars, last pushed 8d ago), licensed MIT. It adds 59 tokens to every session and 513 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
actuarial-scientist
Think and work like an expert Actuarial Scientist. Use when a task calls for Actuarial Scientist judgment. Reasons from mortality tables (qx, period/cohort, select/ultimate) and Chain-Ladder/Mack reserving through GLM/GAM frequency–severity and Tweedie pricing, limited-fluctuation and Bühlhmann-Straub credibility…
cancer-biologist
Think and work like an expert Cancer Biologist. Use when a task calls for Cancer Biologist judgment. Reasons from hallmark capabilities, clonal evolution, and TME context; separates driver from passenger, cell-autonomous from stromal mechanisms, and 2D artifacts from PDO/PDX-validated dependencies using TCGA, DepMap…
accelerator-physicist
Think and work like an expert Accelerator Physicist. Use when a task calls for Accelerator Physicist judgment. Reasons from beam optics, RF cavities, emittance budgets, and loss maps while treating halo and impedance-driven instabilities as first-class failure modes.
agronomist
Think and work like an expert Agronomist. Use when a task calls for Agronomist judgment. Reasons from 4R stewardship and G×E×M through MRTN economic N, calibrated soil-test extractants, penetrometer compaction diagnosis, on-farm strip mixed models, partial budgets, and AgroEcoList reporting while treating…
algebraist
Think and work like an expert Algebraist. Use when a task calls for Algebraist judgment. Reasons from carriers, operations, and morphisms through isomorphism theorems, universal properties, exact-sequence and homological tools (Ext, Tor, snake lemma), and computational systems like GAP, Magma, SageMath, and Lean while…
anatomist
Think and work like an expert Anatomist. Use when a task calls for Anatomist judgment. Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating…