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 TimSimpsonJr/magpie --skill archive-evidencegit clone --depth 1 https://github.com/TimSimpsonJr/magpieWrote 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/timsimpsonjr/magpie/archive-evidence)<a href="https://agentmods.dev/skills/timsimpsonjr/magpie/archive-evidence"><img src="https://agentmods.dev/badge/skills/timsimpsonjr/magpie/archive-evidence/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/timsimpsonjr/magpie/archive-evidence"><img src="https://agentmods.dev/badge/skills/timsimpsonjr/magpie/archive-evidence.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 | $0.00129 | $0.01232 |
| Opus 5 | $0.00064 | $0.00616 |
| Sonnet 5 | $0.00026 | $0.00246 |
| Haiku 4.5 | $0.00013 | $0.00123 |
Grade A, and why
archive-evidence 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 10d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
archive-evidence records provenance at the moment an artifact is received. It calls ONE engine, scripts/evidence.py archive_evidence, which hashes the file, requests a trusted timestamp through an injected Timestamper, writes the local provenance artifacts, and returns a manifest. The SKILL orchestrates the Librarian provenance note from that manifest. evidence.py imports no Librarian; the script writes local files and the skill owns the note.
1. Receipt-first ordering
Hash before any processing. The receipt SHA-256 is the provenance anchor, so archive_evidence computes it first, on receipt, before redaction, conversion, or analysis touches the bytes. Run this skill at intake, not after a pipeline has already rewritten the file. The receipt clock is injected (the now argument), so the recorded received_at is the observation instant, not wall-clock drift inside the engine.
2. The RFC 3161 timestamp
The engine obtains an RFC 3161 trusted timestamp via the injected Timestamper (Rfc3161Timestamper for real use). Option A: the token's message imprint EQUALS the published receipt SHA-256, so a third party can verify with stock tooling. freeTSA (https://freetsa.org/tsr) is the documented default; the bundled freeTSA root verifies the reply on store (verify-on-store). The timestamper fails closed: a non-freeTSA URL with no supplied root does NOT opportunistically trust the reply (it keeps the token but reports status unverified, reason no_root_configured).
The degrade vocabulary is always a status plus a specific reason, never a silent bucket:
- verified -- a token was obtained AND verification passed.
- unverified -- a token was obtained but not verified or verification failed (reason: no_root_configured, verify_failed, imprint_mismatch).
- unavailable -- no token (reason: one of offline, http_error, bad_pki_status, timeout, empty_file, decode_error, dependency_unavailable, read_error).
reason is mandatory whenever status is not verified. The engine never fakes a gen_time and never crashes on a timestamp failure.
What ships with it
2 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.
- 10d ago First seen · 55 lines · 129 tokens per session scan A 350335b26d38
archive-evidence is a skill published in the GitHub repository TimSimpsonJr/magpie (2 stars, last pushed 3mo ago), licensed MIT. It adds 129 tokens to every session and 1,232 once invoked, about $0.0006 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
foia-request-writer
Drafts legally complete public records requests (federal FOIA and all 50 state laws), administrative appeals, and redaction challenge strategies for U.S. government records.
foi-data-request
Drafts a Freedom of Information request specifically targeting datasets, databases, or digital records — written to maximise the chance of receiving complete, machine-readable data rather than summary PDFs or partial tables.
source-verification
Walks through structured verification of sources, claims, images, video, and documents across five verification modes — visual media, documents, anonymous sources, expert credentials, and social media content — using the SIFT framework, forensic metadata inspection, deepfake indicators, C2PA Content Credentials, and…
pdf-table-extractor-brief
Produces a structured extraction plan and clean spreadsheet template for pulling tabular data out of a PDF document — identifying the table structure, defining column headers, flagging extraction pitfalls, and providing a ready-to-use template that ensures the data lands in a consistent, analysable format.
osint-tool-catalog
Produces a categorised catalog of open-source intelligence tools relevant to a journalist's investigation, with practical guidance on what each tool does, when to use it, and what its limitations are.
eu-document-access-builder
Drafts a formal access-to-documents request under the applicable European transparency law for a specified institution and jurisdiction — covering EU Regulation 1049/2001, Germany's IFG, Switzerland's BGÖG, and France's CADA regime — using the correct legal basis, required elements, and procedural language for each.